© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13737
    Prev
    Next
    INDEX
    Explanations

    words associated with religion, mythology, and spirituality

    oai_token-act-pair · gemini-2.0-flash

    perfection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    клопе
    -0.94
     snippetHide
    -0.82
     виправивши
    -0.78
     تضيفلها
    -0.77
     Roskov
    -0.74
     ErrIntOverflow
    -0.74
     <>",
    -0.71
    Vidite
    -0.68
    ]--;
    -0.68
     itſelf
    -0.67
    POSITIVE LOGITS
     perfect
    0.60
     [
    0.49
     perfecte
    0.48
    gin
    0.47
     mu
    0.46
    last
    0.45
    ret
    0.45
     m
    0.45
     perfecto
    0.44
     final
    0.44
    Activations Density 1.897%

    No Known Activations