© 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. 4475
    Prev
    Next
    INDEX
    Explanations

    words related to studies, research, and places around the world.

    oai_token-act-pair · gemini-2.0-flash

    academic excerpts

    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
     (
    -1.07
    ,
    -1.05
     
    -1.03
    .
    -0.94
    '
    -0.93
    <eos>
    -0.93
     M
    -0.91
    ↵↵
    -0.88
     Z
    -0.88
    :
    -0.86
    POSITIVE LOGITS
     Theſe
    1.90
     Efq
    1.83
     myſelf
    1.73
     itſelf
    1.69
     Monfieur
    1.68
     purpoſe
    1.55
     Jefus
    1.55
     auffi
    1.54
     pleaſure
    1.54
    ſelf
    1.52
    Activations Density 4.306%

    No Known Activations