© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    words related to societal status, societal groups, medical status, mechanisms, or art.

    oai_token-act-pair · gemini-2.0-flash

    categories

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     raiſ
    -0.69
     subjects
    -0.66
     itſelf
    -0.65
     iſt
    -0.64
     ſch
    -0.63
     occaf
    -0.63
     countries
    -0.62
     poffible
    -0.62
     places
    -0.60
     branches
    -0.59
    POSITIVE LOGITS
    <bos>
    0.84
     Exactos
    0.74
    Coordenadas
    0.66
    Datuak
    0.63
     disambiguazione
    0.63
    VELOP
    0.60
     cherchés
    0.60
     Exacts
    0.59
    Hochspringen
    0.59
    exprimer
    0.57
    Activations Density 4.593%

    No Known Activations