© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15091
    Prev
    Next
    INDEX
    Explanations

    technical discourse, particularly related to statistics, genetics, or programming

    oai_token-act-pair · gemini-2.0-flash

    9

    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
     Monfieur
    -0.59
     Efq
    -0.54
     Theſe
    -0.53
     raiſ
    -0.48
    ^(@)
    -0.46
     uſed
    -0.45
     Chriftian
    -0.44
     uſe
    -0.44
    ."));
    -0.44
    ſelf
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.90
    TagMode
    0.85
    دانشنامهٔ
    0.84
    AnchorStyles
    0.79
    ScopeManager
    0.77
    gouv
    0.77
    帖最后由
    0.75
    rrggbb
    0.73
    MigrationBuilder
    0.72
    enumi
    0.72
    Activations Density 52.296%

    No Known Activations