© 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
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223496
    Prev
    Next
    INDEX
    Explanations

    grabbing parts of body

    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_10_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
    ر
    0.65
    ла
    0.64
    ться
    0.63
    ي
    0.63
    ם
    0.62
     on
    0.61
    ්‍ර
    0.58
    ዌ
    0.58
    lovely
    0.57
    FISH
    0.57
    POSITIVE LOGITS
     यांचे
    0.52
    ying
    0.52
    ació
    0.50
    的和
    0.49
     Möglich
    0.47
    軞
    0.47
    都有
    0.47
     Guar
    0.47
    徝
    0.46
     వంటి
    0.46
    Activations Density 0.014%

    No Known Activations