© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    words about the degree to which something is true or precise

    oai_token-act-pair · gemini-2.0-flash

    Formal writing

    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
    ighbor
    -0.70
     XNUMX
    -0.69
    AlterField
    -0.66
    delion
    -0.64
     scientifically
    -0.63
     OSError
    -0.61
     StatelessWidget
    -0.60
    hilation
    -0.60
     laajenta
    -0.59
     carbonic
    -0.58
    POSITIVE LOGITS
     समीक्षक
    0.70
    photobucket
    0.60
    ⓧ
    0.54
     corresponden
    0.52
     CURIAM
    0.52
     cima
    0.50
     opro
    0.50
    (',');
    0.49
    :-
    0.49
     Etats
    0.49
    Activations Density 1.426%

    No Known Activations