© 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-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 200007
    Prev
    Next
    INDEX
    Explanations

    past outcome or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    喇
    0.44
    ประ
    0.39
     classific
    0.38
    ຝ
    0.38
     classificação
    0.37
     sectarian
    0.37
     clasificación
    0.36
     жили
    0.36
    $^
    0.35
     classifica
    0.35
    POSITIVE LOGITS
    タンク
    0.42
     பார்க்கலாம்
    0.41
    icit
    0.40
     იქნება
    0.38
     peux
    0.38
    优雅
    0.38
     peut
    0.37
    reib
    0.37
     будет
    0.36
     effortlessly
    0.36
    Activations Density 0.002%

    No Known Activations