© 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. 7212
    Prev
    Next
    INDEX
    Explanations

    positive reviews for services

    oai_token-act-pair · gemini-2.0-flash

    reviews and recommendations

    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
    Negative Logits
     Efq
    -1.33
     Theſe
    -1.09
     ―――――
    -1.07
    يكب
    -1.06
     Jefus
    -1.05
     auffi
    -1.04
    ^(@)
    -1.04
    BibitemShut
    -1.02
     myſelf
    -1.00
     itſelf
    -0.99
    POSITIVE LOGITS
    .
    0.96
    ↵↵
    0.94
    ,
    0.77
     and
    0.77
     (
    0.74
    ↵
    0.73
     ,
    0.71
    <eos>
    0.65
     :
    0.65
    ..
    0.64
    Activations Density 6.429%

    No Known Activations