© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6989
    Prev
    Next
    INDEX
    Explanations

    a mix of punctuation marks, conjunctions, and a few words related to geographical locations or social dynamics.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     he
    -0.59
     per
    -0.57
     o
    -0.53
    -
    -0.52
     Or
    -0.51
    ansky
    -0.51
    ,
    -0.50
     I
    -0.50
     OR
    -0.49
     p
    -0.49
    POSITIVE LOGITS
    
    1.09
     itſelf
    0.97
     Monfieur
    0.96
    that
    0.94
    they
    0.94
     myſelf
    0.93
     Theſe
    0.91
    which
    0.90
    you
    0.90
    not
    0.88
    Activations Density 12.525%

    No Known Activations