© 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. 14283
    Prev
    Next
    INDEX
    Explanations

    LaTeX code, especially equations and mathematical symbols and notation

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    NUMX
    -0.56
    odeficiency
    -0.36
     fat
    -0.35
     e
    -0.35
    ंदीखरीदारी
    -0.35
    最快更新
    -0.34
     mittens
    -0.34
     mengajar
    -0.34
     Fat
    -0.34
     Geller
    -0.34
    POSITIVE LOGITS
     HasFactory
    0.68
    @[+][
    0.67
    MENAFN
    0.63
    __':
    0.63
    .*")]
    0.62
    WithIOException
    0.60
     unknownFields
    0.60
    expandindo
    0.60
    henswürdigkeiten
    0.60
    SourceChecksum
    0.60
    Activations Density 3.873%

    No Known Activations