© 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. 3001
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and words related to death or crime

    oai_token-act-pair · gemini-2.0-flash

    found incapacitated

    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
    évaluateur
    -0.93
     Chwiliwch
    -0.89
     مشين
    -0.85
    __*/
    -0.85
    tvguidetime
    -0.84
     okuyayım
    -0.84
     المعيارى
    -0.82
     оригіналу
    -0.82
     समीक्षाओं
    -0.81
    InSection
    -0.79
    POSITIVE LOGITS
     spraw
    0.43
     st
    0.41
     полу
    0.40
     blo
    0.37
    maris
    0.36
     stre
    0.34
    ides
    0.34
    StreetMap
    0.34
     Sand
    0.33
     sem
    0.33
    Activations Density 2.253%

    No Known Activations