© 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. 57867
    Prev
    Next
    INDEX
    Explanations

    melon and melon types

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ন
    1.59
    न
    1.57
    ン
    1.55
    에
    1.51
    н
    1.45
    า
    1.39
    ב
    1.37
    ن
    1.34
    ک
    1.31
    ת
    1.30
    POSITIVE LOGITS
    f
    1.55
    2
    1.16
    3
    1.05
    もら
    1.03
    v
    1.02
    5
    1.02
    tiger
    1.01
    ot
    0.98
    em
    0.98
    oy
    0.98
    Activations Density 0.006%

    No Known Activations