© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8057
    Prev
    Next
    INDEX
    Explanations

    words or phrases that add emphasis or intensity to the sentences

    oai_token-act-pair · gemini-2.0-flash

    dramatic stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enderror
    -0.88
    LookAnd
    -0.81
    featureID
    -0.77
    CreateMap
    -0.76
    __*/
    -0.75
    parsedMessage
    -0.73
    
    -0.70
     defaultstate
    -0.69
    HtmlAttribute
    -0.68
     MaterialApp
    -0.67
    POSITIVE LOGITS
    ۜ
    0.45
    icznego
    0.43
     dri
    0.40
    雀
    0.38
     couldn
    0.38
    Pages
    0.38
    iedy
    0.37
     chyba
    0.36
     poveznice
    0.36
     ver
    0.36
    Activations Density 0.452%

    No Known Activations