© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141921
    Prev
    Next
    INDEX
    Explanations

    dehumanizing

    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
     De
    1.45
    De
    1.42
     de
    1.39
     де
    1.29
    de
    1.21
    <0xA4>
    1.16
     decon
    1.09
     ده
    1.09
     दे
    1.05
    デ
    1.02
    POSITIVE LOGITS
     पूर्वानु
    0.40
    ساوي
    0.38
    帑
    0.37
     alloying
    0.36
     Alloy
    0.36
     ppb
    0.36
     دوسری
    0.35
    ಕ್ಷಣ
    0.35
     ಪ್ರದೇಶ
    0.35
    कालीन
    0.35
    Activations Density 0.003%

    No Known Activations