© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129767
    Prev
    Next
    INDEX
    Explanations

    wouldn't

    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_6_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
    ir
    1.02
     در
    0.98
    يك
    0.93
    ír
    0.89
    ется
    0.88
    ج
    0.84
    ik
    0.84
     الاح
    0.84
    ية
    0.83
     происходит
    0.83
    POSITIVE LOGITS
    אן
    1.13
    म
    1.07
    א
    1.04
    ம்
    1.02
    מ
    1.01
    ur
    0.99
    כ
    0.96
    ।
    0.89
     racem
    0.89
     fournisseurs
    0.88
    Activations Density 0.002%

    No Known Activations