© 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. 11728
    Prev
    Next
    INDEX
    Explanations

    terms indicating importance, necessity, or lack

    oai_token-act-pair · gemini-2.0-flash

    probability calculations

    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
    awtextra
    -0.99
    GenerationType
    -0.90
    UnusedPrivate
    -0.89
    SourceChecksum
    -0.82
    windowFixed
    -0.82
     doInBackground
    -0.80
     resourceCulture
    -0.79
     OMITBAD
    -0.75
    ftagPool
    -0.75
     defaultstate
    -0.75
    POSITIVE LOGITS
     imp
    0.85
     im
    0.85
    IM
    0.75
     Imp
    0.74
     IM
    0.73
    Imp
    0.71
    im
    0.69
     IMP
    0.69
    Im
    0.69
     Im
    0.63
    Activations Density 8.995%

    No Known Activations