© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 199096
    Prev
    Next
    INDEX
    Explanations

    buttons, radio buttons

    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_4_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
    ↵
    0.95
    ian
    0.68
    c
    0.68
    na
    0.64
     Celestial
    0.62
     போன்றவை
    0.61
     Wraith
    0.61
    ically
    0.60
     Само
    0.59
    縷
    0.59
    POSITIVE LOGITS
    ?
    1.03
    रा
    1.02
    at
    0.98
    তা
    0.96
    of
    0.93
    ור
    0.88
    就
    0.86
    הר
    0.84
    ら
    0.82
    مي
    0.81
    Activations Density 0.001%

    No Known Activations