© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139462
    Prev
    Next
    INDEX
    Explanations

    potato dish preparations

    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_12_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
     potato
    0.55
    ături
    0.53
     आलू
    0.52
    यला
    0.52
    糀
    0.51
    लामा
    0.51
    Potato
    0.50
     repudiandae
    0.50
    ătă
    0.49
    🥔
    0.49
    POSITIVE LOGITS
    Ꮴ
    0.47
    ashed
    0.44
    出力
    0.44
     intuitively
    0.43
    ուն
    0.43
    umper
    0.42
     peruse
    0.42
    unuz
    0.42
    entrySet
    0.42
     بع
    0.42
    Activations Density 0.001%

    No Known Activations