© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13992
    Prev
    Next
    INDEX
    Explanations

    words or unusual characters commonly used in foreign languages other than English

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -1.09
    DoubleQuotes
    -1.00
    DockStyle
    -0.87
    MessageTagHelper
    -0.86
     gynhyrchwyd
    -0.86
    mybatisplus
    -0.85
    RectangleBorder
    -0.84
    ollectionView
    -0.82
    DispatchToProps
    -0.82
    endpush
    -0.81
    POSITIVE LOGITS
    ONT
    0.58
    ont
    0.52
    ・・・・
    0.48
    Link
    0.47
     sudut
    0.47
    ••••
    0.46
    essero
    0.46
     physical
    0.46
    féle
    0.46
     pohod
    0.46
    Activations Density 0.275%

    No Known Activations