© 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. 7363
    Prev
    Next
    INDEX
    Explanations

    code formatting

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    ardio
    -0.58
    dymyr
    -0.56
     Mag
    -0.56
     Fores
    -0.55
     Foer
    -0.54
     qu
    -0.54
    yelitis
    -0.54
    imab
    -0.54
     Der
    -0.54
    endiri
    -0.53
    POSITIVE LOGITS
     végétale
    0.64
     propOrder
    0.63
    FunctionFlags
    0.63
     Egli
    0.60
     sauvage
    0.60
     termica
    0.59
     AssemblyCulture
    0.58
    principalColumn
    0.56
     femininas
    0.56
     împre
    0.55
    Activations Density 0.831%

    No Known Activations