© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2370
    Prev
    Next
    INDEX
    Explanations

    questions using the phrase "what do you"

    oai_token-act-pair · gemini-2.0-flash

    the question "what do"

    np_token-act-pair-logits · gpt-4o-mini

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     it
    -0.87
     оно
    -0.84
    它
    -0.79
     dalamnya
    -0.69
     něm
    -0.67
     său
    -0.64
     нём
    -0.64
    It
    -0.61
    因为它
    -0.59
     ervan
    -0.59
    POSITIVE LOGITS
     these
    0.82
     you
    0.78
     they
    0.73
    ंदीखरीदारी
    0.67
    ValueGenerated
    0.66
    migrationBuilder
    0.65
     we
    0.64
     others
    0.63
     THESE
    0.60
    these
    0.59
    Activations Density 0.954%

    No Known Activations