© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10161
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and statistical terminology.

    oai_token-act-pair · gemini-2.0-flash

    econometrics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     FetchType
    -0.68
    (!__
    -0.68
     couverts
    -0.67
     positifs
    -0.63
    Zeneca
    -0.63
     Coupled
    -0.60
    SharedCtor
    -0.59
     Polsek
    -0.56
     rencontré
    -0.56
    andExpect
    -0.56
    POSITIVE LOGITS
     migrator
    0.48
    AutoScaleMode
    0.45
     ffilmiau
    0.44
    soort
    0.44
     utafitiHapana
    0.43
     AssemblyCulture
    0.43
     dep
    0.43
    VideoCapture
    0.42
     Brownian
    0.41
    aday
    0.41
    Activations Density 8.280%

    No Known Activations