© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10576
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, especially those involving division

    oai_token-act-pair · gemini-2.0-flash

    Calculations and technical information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    TagMode
    -0.59
     <<<<<<<<<<<<<<
    -0.54
    expandindo
    -0.52
     שוליים
    -0.50
     the
    -0.50
    :✨
    -0.49
    ´)
    -0.48
    Personensuche
    -0.48
     >=",
    -0.47
    Lähteet
    -0.47
    POSITIVE LOGITS
    [
    0.60
    (
    0.56
    <?
    0.50
     suono
    0.49
    -”
    0.49
    resave
    0.46
    EX
    0.46
    ”—
    0.44
    Ex
    0.44
    jspx
    0.44
    Activations Density 7.658%

    No Known Activations