© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143398
    Prev
    Next
    INDEX
    Explanations

    Kib

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ಿಗ
    0.44
    SAND
    0.43
    +/
    0.43
     tanta
    0.40
     Santé
    0.40
     disappointments
    0.39
    VENUE
    0.38
     Usuario
    0.38
     Sandusky
    0.38
    vas
    0.37
    POSITIVE LOGITS
     enlight
    0.39
    渐
    0.38
     radi
    0.37
    名称
    0.36
     downt
    0.36
     före
    0.36
     renversement
    0.36
    בת
    0.36
     enlightenment
    0.36
    ciphertext
    0.36
    Activations Density 0.000%

    No Known Activations