© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11603
    Prev
    Next
    INDEX
    Explanations

    numerical data including scientific constants, mathematical equations, and numbers in lists

    oai_token-act-pair · gemini-2.0-flash

    Days of the week

    np_max-act-logits · gemini-2.0-flash

    say "numbers" Method used: 2 — because tokens after the max-activating token are numeric — say "numbers"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ninth
    -0.79
     tenth
    -0.74
     Tenth
    -0.74
     ten
    -0.73
     Ten
    -0.71
     Ninth
    -0.69
    Ten
    -0.68
     nine
    -0.68
    ten
    -0.65
     eighth
    -0.65
    POSITIVE LOGITS
     Tuesday
    0.66
     Wednesday
    0.65
    Tuesday
    0.63
    Wednesday
    0.58
    Portail
    0.57
    AnchorStyles
    0.56
     TUESDAY
    0.55
    2
    0.54
     Dienstag
    0.54
     martes
    0.54
    Activations Density 4.309%

    No Known Activations