© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6089
    Prev
    Next
    INDEX
    Explanations

    python code generation

    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_39_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
     വായി
    0.39
    瀏
    0.37
    খিক
    0.37
    CHARGE
    0.36
     근무
    0.36
    oby
    0.36
     खनिज
    0.35
     ≤
    0.35
     तुम्ही
    0.35
    彻
    0.34
    POSITIVE LOGITS
     Legendre
    0.40
    ๋า
    0.40
     patriot
    0.40
     Patricia
    0.39
     peculiarity
    0.38
    比例
    0.38
    Patricia
    0.38
    جاه
    0.38
     Hitch
    0.38
    μοι
    0.38
    Activations Density 0.035%

    No Known Activations