© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162669
    Prev
    Next
    INDEX
    Explanations

    names, places, and technical terms

    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_2_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
    1.08
    2
    1.02
    ing
    0.94
    t
    0.87
    f
    0.87
    ה
    0.86
    ۔
    0.85
     powied
    0.82
    ru
    0.80
    لا
    0.80
    POSITIVE LOGITS
    า
    1.02
    та
    0.88
    த்தில்
    0.86
    서
    0.83
     malicious
    0.81
    情况
    0.78
    ิ
    0.77
    '
    0.75
     delante
    0.75
    kách
    0.74
    Activations Density 0.000%

    No Known Activations