© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7869
    Prev
    Next
    INDEX
    Explanations

    words associated with authenticity, thoroughness, and accuracy

    oai_token-act-pair · gemini-2.0-flash

    genuine or thoroughly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     biotic
    -0.82
     speciation
    -0.81
     mitotic
    -0.79
     cardinality
    -0.78
     Macromolecules
    -0.77
     anthracite
    -0.77
     demurrer
    -0.77
     Bayard
    -0.76
     virtuous
    -0.75
     Carboniferous
    -0.75
    POSITIVE LOGITS
    <bos>
    1.91
    Билгалдахарш
    0.63
     to
    0.58
    ')):
    0.57
     latter
    0.57
     ویکی‌پدیای
    0.57
    jface
    0.54
    '})
    0.54
     often
    0.52
    '}}
    0.52
    Activations Density 1.689%

    No Known Activations