© 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. 80882
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    伪
    0.42
    executed
    0.41
     الاعدادي
    0.39
    intercept
    0.38
    长时间
    0.37
    违
    0.37
    )^{(
    0.37
     Swarovski
    0.37
    Volkswagen
    0.36
     दुरुपयोग
    0.36
    POSITIVE LOGITS
     emplacement
    0.41
    邬
    0.40
     Sun
    0.39
     cutoff
    0.38
    cutoff
    0.38
     monomer
    0.37
     অক্ষর
    0.37
    झ
    0.37
    imeo
    0.37
     tabulation
    0.36
    Activations Density 0.005%

    No Known Activations