© 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. 75876
    Prev
    Next
    INDEX
    Explanations

    colors and their values

    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
     પોલી
    0.36
     kebijakan
    0.36
    Skin
    0.35
    丑
    0.35
    jat
    0.34
     SKIN
    0.34
     preg
    0.34
    អ៊ី
    0.34
     acclimat
    0.33
     skin
    0.33
    POSITIVE LOGITS
    leader
    0.37
    ראש
    0.36
     потім
    0.35
    誐
    0.35
     ජී
    0.34
    ໄວ
    0.34
    زاده
    0.34
     далее
    0.34
    subtract
    0.33
     సామ
    0.33
    Activations Density 0.007%

    No Known Activations