© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69676
    Prev
    Next
    INDEX
    Explanations

    gradle

    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_51_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
    uously
    0.40
    ゾーン
    0.39
    ﻼ
    0.39
    elling
    0.38
    iovascular
    0.38
    ELIST
    0.38
    лаб
    0.38
    ാണ്
    0.38
    耂
    0.38
    ierten
    0.38
    POSITIVE LOGITS
    isie
    0.44
    stride
    0.42
    ście
    0.40
    gré
    0.40
    phis
    0.40
    ȝ
    0.40
    Narc
    0.39
    રિ
    0.38
    Files
    0.38
     ٹیک
    0.38
    Activations Density 0.001%

    No Known Activations