© 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. 220127
    Prev
    Next
    INDEX
    Explanations

    liquid or powdered ingredients

    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
     while
    0.39
    ﹑
    0.39
     searchValue
    0.38
     примерно
    0.37
     هیچ
    0.37
     Werte
    0.37
     Agnes
    0.36
     ३
    0.36
     Kalam
    0.36
     ૩
    0.36
    POSITIVE LOGITS
    newblock
    0.39
    лій
    0.38
    blend
    0.37
     Подо
    0.37
     Blend
    0.36
     fast
    0.35
     Calls
    0.35
     khoan
    0.35
    ᄏ
    0.35
    
    0.35
    Activations Density 0.015%

    No Known Activations