© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4630
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "reason" or "reasons"

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     reasons
    -0.74
     reason
    -0.70
     why
    -0.68
    reasons
    -0.67
    why
    -0.64
    Reason
    -0.60
    原因
    -0.59
     Gründe
    -0.59
    Warum
    -0.59
    REASON
    -0.57
    POSITIVE LOGITS
    complexContent
    0.78
     juridiques
    0.70
     sexuales
    0.68
    LookAnd
    0.66
     незавершена
    0.66
    InjectAttribute
    0.65
     jurí
    0.65
     térm
    0.64
     giuri
    0.64
     financières
    0.63
    Activations Density 7.936%

    No Known Activations