© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13490
    Prev
    Next
    INDEX
    Explanations

    a wide range of seemingly unrelated terms including copyright notices, military terms, place names, and names

    oai_token-act-pair · gemini-2.0-flash

    government and administration

    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
    atifs
    -0.56
    يكب
    -0.54
    bandcamp
    -0.54
    Affirmed
    -0.52
     Am
    -0.50
     k
    -0.49
    iją
    -0.48
    ыгана
    -0.47
    esez
    -0.47
    mpion
    -0.47
    POSITIVE LOGITS
    PerformLayout
    0.66
    Personendaten
    0.61
     Diſ
    0.59
     purpoſe
    0.59
    AndEndTag
    0.58
    ?")
    0.57
    ByPrimaryKey
    0.57
     "];
    0.57
    ñora
    0.57
     StatefulWidget
    0.56
    Activations Density 1.824%

    No Known Activations