© 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. 3003
    Prev
    Next
    INDEX
    Explanations

    content about struggling, fighting, war, or competition.

    oai_token-act-pair · gemini-2.0-flash

    fight

    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
    MigrationBuilder
    -0.71
    DockStyle
    -0.62
     SwitchCompat
    -0.54
    spaceBetween
    -0.54
     fight
    -0.53
    utilisons
    -0.52
    WebServlet
    -0.52
    ళ్
    -0.50
    peutic
    -0.50
     internetowa
    -0.50
    POSITIVE LOGITS
    twimg
    0.56
    hdessä
    0.54
     to
    0.54
     ["",
    0.52
    orianCalendar
    0.49
    endfor
    0.48
     OFDb
    0.47
    ExecuteReader
    0.46
    differential
    0.46
     antiquity
    0.45
    Activations Density 7.919%

    No Known Activations