© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    terms related to research studies or scientific reports

    oai_token-act-pair · gemini-2.0-flash

    scientific text

    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
     means
    -0.96
     Means
    -0.91
    means
    -0.82
     MEANS
    -0.78
    Means
    -0.75
     Says
    -0.71
     says
    -0.65
    Says
    -0.62
     Allows
    -0.61
     Continues
    -0.59
    POSITIVE LOGITS
     ujednoznacz
    0.71
    kloped
    0.64
    chymal
    0.60
    jsxFileName
    0.60
    PerformLayout
    0.60
    iastes
    0.60
    ReusableCell
    0.59
    are
    0.58
     disambiguazione
    0.57
     ModelExpression
    0.56
    Activations Density 15.733%

    No Known Activations