© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139919
    Prev
    Next
    INDEX
    Explanations

    one-to-one correspondence or onto

    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_37_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
     dijete
    0.40
    یدار
    0.39
    acyjne
    0.38
    臬
    0.38
     मिताली
    0.38
    avr
    0.37
    ariam
    0.37
     ஏரா
    0.37
    constraintlayout
    0.37
     CrL
    0.36
    POSITIVE LOGITS
     onto
    0.52
     into
    0.46
    into
    0.42
    onto
    0.40
    上に
    0.40
    上
    0.40
    Into
    0.38
     Lire
    0.38
     founders
    0.37
    founders
    0.37
    Activations Density 0.000%

    No Known Activations