© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10030
    Prev
    Next
    INDEX
    Explanations

    contractions ending in "t" or "'re", and "we"

    oai_token-act-pair · gemini-2.0-flash

    t

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    still
    -0.57
     pronto
    -0.54
     همچ
    -0.50
    toJSONString
    -0.48
     uska
    -0.48
    それとも
    -0.47
     Still
    -0.47
    never
    -0.47
     not
    -0.46
     Either
    -0.46
    POSITIVE LOGITS
     necessarily
    0.84
    tvguidetime
    0.82
    uxxxx
    0.71
     even
    0.67
     technically
    0.64
     necesar
    0.59
    VolleyError
    0.58
     Anexo
    0.56
     exactly
    0.55
    Билгалдахарш
    0.55
    Activations Density 0.894%

    No Known Activations