© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9966
    Prev
    Next
    INDEX
    Explanations

    dates and references to section numbers of legal codes

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Meksiku
    -0.60
     onOptions
    -0.59
    GenerationType
    -0.55
     BoxFit
    -0.54
    BrowserModule
    -0.53
    interopRequire
    -0.53
    ILayout
    -0.52
    protoimpl
    -0.51
    DoubleQuotes
    -0.51
    preventDefault
    -0.50
    POSITIVE LOGITS
     nine
    0.61
     eight
    0.60
     electing
    0.59
     ten
    0.56
     letting
    0.56
     NINE
    0.55
     arriving
    0.53
     conceding
    0.53
     againſt
    0.53
     chofe
    0.53
    Activations Density 5.657%

    No Known Activations