© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10313
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to the author and words of encouragement or possibility.

    oai_token-act-pair · gemini-2.0-flash

    toughness

    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
     Normdatei
    -0.80
    出版年
    -0.79
     AssemblyCompany
    -0.79
     actualité
    -0.68
     complé
    -0.65
    attenzione
    -0.65
     stratégique
    -0.64
     myſelf
    -0.63
    UnusedPrivate
    -0.63
     complémentaires
    -0.63
    POSITIVE LOGITS
     tough
    1.08
    Tough
    0.94
     Tough
    0.92
    tough
    0.91
     bra
    0.79
     brave
    0.77
     toughness
    0.75
     hardy
    0.75
     toughest
    0.74
     tougher
    0.73
    Activations Density 1.717%

    No Known Activations