© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4173
    Prev
    Next
    INDEX
    Explanations

    words related to scientific analysis and reports

    oai_token-act-pair · gemini-2.0-flash

    origins and derivations

    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
    NOPQRST
    -0.88
     Italijani
    -0.75
    ngths
    -0.75
    amentals
    -0.73
    writeFieldEnd
    -0.70
    ThemeOverlay
    -0.69
     répondu
    -0.69
     rempliss
    -0.69
    actionMode
    -0.68
    tshire
    -0.68
    POSITIVE LOGITS
     equally
    0.66
     first
    0.66
    on
    0.59
     invariably
    0.54
     variously
    0.52
     first
    0.52
     incessantly
    0.51
    first
    0.51
     successively
    0.50
     uniformly
    0.50
    Activations Density 8.922%

    No Known Activations