© 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. 14878
    Prev
    Next
    INDEX
    Explanations

    words and phrases of emphasis or strong adjectives or nouns with positive or negative association

    oai_token-act-pair · gemini-2.0-flash

    Articles and storytelling

    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
    ècie
    -0.62
     مرئيه
    -0.57
    ToRefresh
    -0.55
    enderror
    -0.52
    ="#"
    -0.48
    phemy
    -0.48
     spun
    -0.47
    wered
    -0.47
    blica
    -0.47
    windowFixed
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.88
     fubject
    0.74
     houſe
    0.65
     ftate
    0.60
     ſeveral
    0.60
     perfons
    0.57
     Shakspeare
    0.56
     Hift
    0.56
     ſtate
    0.56
     Monfieur
    0.56
    Activations Density 16.086%

    No Known Activations