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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45518
    Prev
    Next
    INDEX
    Explanations

    classification answers

    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_22_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
     imparting
    0.45
    }`,
    0.44
    臘
    0.44
     brushing
    0.43
     communs
    0.43
     anderen
    0.42
     innych
    0.42
     other
    0.41
     \,.
    0.41
     mientras
    0.41
    POSITIVE LOGITS
    యం
    0.39
    عل
    0.39
    Му
    0.38
    Mush
    0.38
     బల
    0.38
    ණ්
    0.37
    ऍ
    0.37
    程序员
    0.37
    Сер
    0.37
    ಸ್
    0.36
    Activations Density 0.001%

    No Known Activations