© 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. 10059
    Prev
    Next
    INDEX
    Explanations

    a variety of punctuation and conjunction words

    oai_token-act-pair · gemini-2.0-flash

    Code, URL punctuation

    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
    olverine
    -0.75
    PreferredItem
    -0.73
    Portale
    -0.68
     gynnwys
    -0.64
    ρίες
    -0.63
    InstrumentedTest
    -0.63
    ULATE
    -0.61
    idoscope
    -0.61
     makeStyles
    -0.60
    toHave
    -0.60
    POSITIVE LOGITS
    cioso
    0.42
    astéroïdes
    0.40
    multer
    0.39
    SourceChecksum
    0.37
    VIAF
    0.36
     Bo
    0.34
    갓
    0.33
     Roskov
    0.33
    siapkan
    0.32
     grava
    0.32
    Activations Density 0.590%

    No Known Activations