© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132782
    Prev
    Next
    INDEX
    Explanations

    fitting within limits

    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
     поме
    1.30
     вме
    1.26
    容
    1.20
     вмі
    1.06
     cabe
    1.05
     χω
    1.04
     Вме
    0.99
     fits
    0.88
     помі
    0.87
     fit
    0.82
    POSITIVE LOGITS
    龰
    0.40
    γη
    0.40
     আচ্ছ
    0.39
    িক্ষ
    0.38
     Hurd
    0.38
    gol
    0.37
     Kyr
    0.36
    TRI
    0.35
    Gol
    0.35
     وانا
    0.34
    Activations Density 0.011%

    No Known Activations