© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209491
    Prev
    Next
    INDEX
    Explanations

    excels" or "excitability"

    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_5_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
    ه
    2.03
    ↵↵
    1.97
    t
    1.90
    in
    1.79
    3
    1.63
    a
    1.55
    9
    1.51
    ה
    1.38
    .
    1.37
    es
    1.29
    POSITIVE LOGITS
    itian
    1.20
    ம்
    1.19
    '
    1.11
    ం
    1.05
    ור
    1.03
    డాది
    1.02
    ટર
    1.02
    ം
    1.02
    ס
    0.98
    ască
    0.95
    Activations Density 0.001%

    No Known Activations