© 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. 6702
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    oai_token-act-pair · gemini-2.0-flash

    backslash

    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
     Púb
    -0.52
     */;
    -0.50
     imobili
    -0.50
     deceased
    -0.49
     insensible
    -0.48
    )))));
    -0.48
     predis
    -0.47
     Widodo
    -0.47
    gebied
    -0.47
    Ÿ
    -0.47
    POSITIVE LOGITS
    clearpage
    0.77
    eqref
    0.69
    vfill
    0.68
    usepackage
    0.68
    bigskip
    0.68
    xymatrix
    0.67
    TagMode
    0.67
    theoremstyle
    0.64
    PostExecute
    0.63
    notag
    0.63
    Activations Density 2.524%

    No Known Activations