© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67182
    Prev
    Next
    INDEX
    Explanations

    probability

    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_46_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
    SqlServer
    0.42
     singolo
    0.41
     جميع
    0.40
    物の
    0.40
    すべて
    0.40
    馏
    0.39
    phenoxymethyl
    0.39
     ትንሽ
    0.39
     영어
    0.38
    別の
    0.38
    POSITIVE LOGITS
    lyde
    0.38
    ☞
    0.38
     ነው
    0.38
    在地
    0.38
     стать
    0.37
    பா
    0.36
    Karte
    0.36
    dü
    0.36
    ｅ
    0.35
    োদয়
    0.35
    Activations Density 0.009%

    No Known Activations