© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    legal and organizational jargon, often including "District," "Company," "Corporation," and sometimes names or abbreviations.

    oai_token-act-pair · gemini-2.0-flash

    District

    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
     itſelf
    -1.67
     myſelf
    -1.63
     purpoſe
    -1.53
    ſelf
    -1.49
     Jefus
    -1.45
     houſe
    -1.44
     Majefty
    -1.41
     raiſ
    -1.41
     ſtate
    -1.38
     himſelf
    -1.38
    POSITIVE LOGITS
     (
    0.88
    (
    0.84
    “
    0.84
    !
    0.84
    .
    0.81
     og
    0.79
    :
    0.79
     k
    0.79
     d
    0.78
    -
    0.78
    Activations Density 0.925%

    No Known Activations