© 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. 5737
    Prev
    Next
    INDEX
    Explanations

    batting eyelashes

    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
     beads
    0.42
    स्वर
    0.40
    ὀ
    0.39
    紅
    0.39
     सड़क
    0.38
     Ξ
    0.37
     nagy
    0.36
     ஆர்
    0.36
    ㈠
    0.36
     alın
    0.36
    POSITIVE LOGITS
     lashes
    1.02
     lash
    0.99
     Lash
    0.97
     eyelashes
    0.97
     lashed
    0.93
    lashes
    0.86
     eyelash
    0.84
    睫
    0.84
     false
    0.73
    lash
    0.71
    Activations Density 0.003%

    No Known Activations