© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11918
    Prev
    Next
    INDEX
    Explanations

    words that describe familial relationships

    oai_token-act-pair · gemini-2.0-flash

    family members

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.45
    kozó
    -0.44
     amet
    -0.43
    tilde
    -0.43
     rağmen
    -0.42
     Dro
    -0.41
    widetilde
    -0.41
     suun
    -0.40
     فا
    -0.39
    tigo
    -0.39
    POSITIVE LOGITS
     ModelExpression
    0.85
    RenderAtEndOf
    0.80
    principalColumn
    0.71
     مشين
    0.66
    ArgsConstructor
    0.62
    PRNewswire
    0.62
     nakalista
    0.60
    Lähteet
    0.58
    DockStyle
    0.57
    fromnode
    0.57
    Activations Density 0.079%

    No Known Activations