© 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. 219915
    Prev
    Next
    INDEX
    Explanations

    mix or combine 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
     combining
    0.53
    Combining
    0.44
    组合
    0.43
     Combining
    0.41
    ရှိ
    0.41
     combine
    0.40
     combines
    0.40
    ͎
    0.39
    combin
    0.39
     combing
    0.37
    POSITIVE LOGITS
    شتغل
    0.39
     ஃப
    0.38
     hé
    0.37
     വള
    0.36
    ALTERNATIVNAMEN
    0.36
     professionnels
    0.36
     പട്ട
    0.36
     mehreren
    0.36
    كيت
    0.35
     فعال
    0.35
    Activations Density 0.003%

    No Known Activations