© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24190
    Prev
    Next
    INDEX
    Explanations

    porous and porous medium

    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_10_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
    ंशी
    0.67
    ﻼ
    0.65
    穢
    0.65
    ंच
    0.65
    ܂
    0.65
    संस्करण
    0.64
    лі
    0.63
    ('');
    0.63
    क्के
    0.62
    駛
    0.62
    POSITIVE LOGITS
    0.91
    us
    0.80
     that
    0.79
     amminist
    0.73
     ombre
    0.73
     altro
    0.72
     agente
    0.71
     auteur
    0.71
     amo
    0.70
     astronaut
    0.69
    Activations Density 0.021%

    No Known Activations