© 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. 903
    Prev
    Next
    INDEX
    Explanations

    mostly non-English words and the preposition "in"

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and other languages

    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
     nî
    -0.44
    vait
    -0.44
    beep
    -0.42
     <",
    -0.42
     Mello
    -0.42
    CancelButton
    -0.42
     "}";
    -0.41
     kesadaran
    -0.41
    ComponentName
    -0.41
    errno
    -0.41
    POSITIVE LOGITS
     Roskov
    0.96
     kasarigan
    0.91
    contentLoaded
    0.81
     betweenstory
    0.77
    expandindo
    0.75
     виправивши
    0.74
     AspNetCore
    0.69
    DeleteBehavior
    0.67
    SourceChecksum
    0.66
    ScopeManager
    0.66
    Activations Density 0.232%

    No Known Activations