© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220566
    Prev
    Next
    INDEX
    Explanations

    SMS procedure calls

    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_31_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
    uerre
    0.31
    ciri
    0.30
    liberal
    0.30
     그러면
    0.29
    ANSWER
    0.29
    回答
    0.29
    𝖽
    0.29
    rente
    0.28
     নিরপেক্ষ
    0.28
     כא
    0.28
    POSITIVE LOGITS
     fiasco
    0.33
    ➙
    0.33
     invariants
    0.31
     stipulates
    0.31
     MAGIC
    0.31
    >>)
    0.31
     ✨
    0.31
    Injector
    0.31
     tragic
    0.30
    🍰
    0.30
    Activations Density 0.000%

    No Known Activations