© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36100
    Prev
    Next
    INDEX
    Explanations

    my purpose is to provide

    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_11_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
    EVEN
    0.67
    d
    0.66
    ELEASE
    0.61
    g
    0.59
    HCl
    0.57
    ወ
    0.57
     ప్ర
    0.54
    OUIS
    0.54
    .。
    0.54
     इसमें
    0.54
    POSITIVE LOGITS
    ،
    0.61
     aparato
    0.57
    ﻪ
    0.57
    azione
    0.57
    िना
    0.56
     ocorre
    0.56
    از
    0.56
     entlang
    0.56
    ierten
    0.55
     αυτές
    0.55
    Activations Density 0.006%

    No Known Activations