© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43956
    Prev
    Next
    INDEX
    Explanations

    gritty feeling or sand in eyes

    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_13_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
    ement
    0.57
    e
    0.54
    ochrome
    0.53
    puzzle
    0.53
    6
    0.51
    <0x80>
    0.50
    вые
    0.50
    en
    0.50
    back
    0.49
     wynika
    0.49
    POSITIVE LOGITS
     історії
    0.54
     prosecuting
    0.54
     stopwords
    0.54
    ॢ
    0.51
     اخرى
    0.50
     السيارات
    0.50
     автомобі
    0.49
     साल
    0.48
    鐩
    0.48
     particulates
    0.48
    Activations Density 0.039%

    No Known Activations