© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7168
    Prev
    Next
    INDEX
    Explanations

    citations for scientific papers

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.84
    SharedDtor
    -0.84
     nahilalakip
    -0.83
    fromnode
    -0.82
     unknownFields
    -0.80
    utilisons
    -0.80
     مشين
    -0.78
    Erreferentziak
    -0.76
    oredCriteria
    -0.74
    windowFixed
    -0.74
    POSITIVE LOGITS
    tryk
    0.38
    TELL
    0.38
    ushin
    0.35
    みました
    0.35
    PreAuthorize
    0.34
    gese
    0.33
    lekt
    0.33
     Second
    0.33
    adomo
    0.33
    splash
    0.32
    Activations Density 1.625%

    No Known Activations