© 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. 209748
    Prev
    Next
    INDEX
    Explanations

    Kowloon Peninsula

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ر
    1.43
    ن
    1.40
    is
    1.37
    ות
    1.35
    in
    1.30
    er
    1.30
    ர்
    1.29
    ہ
    1.28
    न
    1.25
    ق
    1.23
    POSITIVE LOGITS
    1.74
    3
    1.39
    '
    1.27
    2
    0.99
    이다
    0.96
    EO
    0.91
    d
    0.86
    .
    0.86
    Bezier
    0.85
    6
    0.84
    Activations Density 0.000%

    No Known Activations