© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and ideas related to societal and individual identity, belonging, or status

    oai_token-act-pair · gemini-2.0-flash

    position, behavior, status

    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
     Anſ
    -0.89
     Theſe
    -0.85
     Jefus
    -0.84
     fubject
    -0.83
     auffi
    -0.82
     Majefty
    -0.81
     Reſ
    -0.80
     photolibrary
    -0.79
     fevere
    -0.79
     poffe
    -0.79
    POSITIVE LOGITS
     there
    0.57
    .
    0.56
    ,
    0.54
    us
    0.54
     (
    0.53
     in
    0.53
    ...
    0.52
     E
    0.52
     and
    0.51
    iss
    0.51
    Activations Density 27.365%

    No Known Activations