© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7305
    Prev
    Next
    INDEX
    Explanations

    code related to directory traces

    oai_token-act-pair · gemini-2.0-flash

    trace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Drawn
    -0.70
     drawn
    -0.68
    клопе
    -0.67
     againſt
    -0.66
    Drawn
    -0.66
     draw
    -0.62
    Draws
    -0.62
     myſelf
    -0.61
    Fordítás
    -0.61
     pousse
    -0.60
    POSITIVE LOGITS
     intptr
    0.61
    Hentet
    0.58
    ardoor
    0.54
    windowFixed
    0.54
     initComponents
    0.54
    SupportActionBar
    0.54
    timewa
    0.54
    లాలు
    0.53
    providedIn
    0.53
    SerializedName
    0.52
    Activations Density 0.374%

    No Known Activations