© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8128
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, data, studies, experiments, and research findings.

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sum
    -0.42
    koin
    -0.41
     Sum
    -0.41
    <bos>
    -0.40
    Sklici
    -0.38
     G
    -0.36
    Sum
    -0.35
    Hentet
    -0.35
     Pas
    -0.34
    ysuckle
    -0.33
    POSITIVE LOGITS
    Autoritní
    0.84
     disambiguazione
    0.81
    exitRule
    0.80
    jooq
    0.80
     betweenstory
    0.76
    MessageOf
    0.74
     "..\..\..\
    0.72
    BeginContext
    0.68
    AndEndTag
    0.68
     "..\..\
    0.67
    Activations Density 7.909%

    No Known Activations