© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111566
    Prev
    Next
    INDEX
    Explanations

    grilling food or equipment

    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_2_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
    asyon
    1.02
    心的
    0.96
    werte
    0.94
    ní
    0.90
    من
    0.89
    deren
    0.88
    >}
    0.86
    izamos
    0.86
    izing
    0.86
    lage
    0.86
    POSITIVE LOGITS
    น
    1.77
    ب
    1.74
    ر
    1.59
    ות
    1.55
    د
    1.38
    ة
    1.35
    ন
    1.34
     to
    1.30
    ج
    1.30
    ນ
    1.29
    Activations Density 0.001%

    No Known Activations