© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10142
    Prev
    Next
    INDEX
    Explanations

    baby, milk, feeding, oral, tongue, spit

    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_40_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
    鄔
    0.43
     Nutt
    0.42
     Recorded
    0.41
     Fuse
    0.40
    벽
    0.40
    ombra
    0.39
     Watering
    0.39
    footer
    0.39
     footer
    0.39
     unaltered
    0.39
    POSITIVE LOGITS
     tongue
    0.51
     spit
    0.49
     массив
    0.43
    tong
    0.43
     मिल्क
    0.42
    舌
    0.42
     reflux
    0.41
     mong
    0.41
     Tongue
    0.40
     spits
    0.40
    Activations Density 0.045%

    No Known Activations