© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    citations and references from legal documents.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    MLLoader
    -0.74
     bag
    -0.72
    ConstraintMaker
    -0.71
     buck
    -0.66
    :✨
    -0.63
    leine
    -0.63
    RepeatedField
    -0.61
     chuck
    -0.59
     deck
    -0.59
     bed
    -0.59
    POSITIVE LOGITS
     quelcon
    0.58
     behö
    0.52
    <bos>
    0.51
     prochaines
    0.51
     dezelve
    0.50
     épu
    0.50
     eenige
    0.49
     igång
    0.48
     nég
    0.48
     Epis
    0.48
    Activations Density 49.918%

    No Known Activations