© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13438
    Prev
    Next
    INDEX
    Explanations

    measures and solutions

    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_13_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
     santos
    0.32
     status
    0.32
    زال
    0.31
     voci
    0.29
    цем
    0.29
    婊
    0.28
     productivity
    0.28
    圣
    0.28
    ందని
    0.28
     lè
    0.28
    POSITIVE LOGITS
     उपाय
    0.38
    ALTERNATIV
    0.32
     उपायों
    0.32
     thoughtful
    0.31
    ؟
    0.31
     എന്നാൽ
    0.30
     thậm
    0.30
     অথবা
    0.30
     medidas
    0.30
     biện
    0.29
    Activations Density 0.115%

    No Known Activations