© 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. 9479
    Prev
    Next
    INDEX
    Explanations

    hyphens, quotes, parenthesis and other punctuation when they are used around numbers

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    in
    -1.31
    IN
    -0.88
     يتيمه
    -0.73
    inl
    -0.73
    on
    -0.71
    ConstraintMaker
    -0.69
    en
    -0.64
    inb
    -0.63
    out
    -0.59
    inon
    -0.59
    POSITIVE LOGITS
    faßt
    0.60
    this
    0.56
    acious
    0.54
    choly
    0.51
    asta
    0.49
    achen
    0.48
    verns
    0.48
    atech
    0.47
     daß
    0.47
    acy
    0.46
    Activations Density 14.481%

    No Known Activations