© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    sentences where a person expresses an opinion or reaction or expresses intent

    oai_token-act-pair · gemini-2.0-flash

    Informal blog or social media

    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
    uff
    -0.41
    サ
    -0.41
    zor
    -0.40
    pters
    -0.40
    ciata
    -0.39
     }^{[
    -0.39
     heraus
    -0.38
    あ
    -0.38
     dikk
    -0.38
     Vals
    -0.38
    POSITIVE LOGITS
    Carriera
    0.81
     beginnetje
    0.79
    Personendaten
    0.77
    principalColumn
    0.75
     uska
    0.73
     autorytatywna
    0.70
     FetchType
    0.67
     ComVisible
    0.67
    SourceChecksum
    0.67
    ^(@)
    0.67
    Activations Density 1.263%

    No Known Activations