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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1085
    Prev
    Next
    INDEX
    Explanations

    formulas in LaTeX markup

    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
    essoas
    -0.53
     Aran
    -0.52
    deinit
    -0.50
    zyw
    -0.49
    Aran
    -0.48
    Lycka
    -0.48
    NECT
    -0.48
    caman
    -0.47
    namiento
    -0.47
    PERF
    -0.47
    POSITIVE LOGITS
     незавершена
    0.75
    InjectAttribute
    0.69
    protoimpl
    0.66
     &___
    0.64
    ViewImports
    0.63
    Datuak
    0.62
     linkovi
    0.61
    帖最后由
    0.60
    %)$
    0.60
    الإنجليزية
    0.60
    Activations Density 3.721%

    No Known Activations