© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129831
    Prev
    Next
    INDEX
    Explanations

    know

    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_50_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
     μεγάλη
    0.42
    pager
    0.38
     خلاص
    0.38
    𒈠
    0.38
    ρύ
    0.37
     विवे
    0.37
    ខ្ល
    0.36
    শিয়ার
    0.36
     keyDown
    0.35
    🥐
    0.35
    POSITIVE LOGITS
    頤
    0.37
    hee
    0.37
    િ
    0.37
     नर
    0.36
     Fred
    0.36
     Salem
    0.36
    NYSE
    0.36
     Detroit
    0.35
     Mour
    0.35
    ony
    0.35
    Activations Density 0.005%

    No Known Activations