© 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
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 118756
    Prev
    Next
    INDEX
    Explanations

    portion of

    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_27_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
    경기도
    0.33
    കേന്ദ്ര
    0.32
    Strateg
    0.30
    Fen
    0.30
    Behind
    0.29
    ٻ
    0.29
    罫
    0.29
    Decoder
    0.28
    weds
    0.28
     Cowan
    0.28
    POSITIVE LOGITS
    ан
    0.28
     Sw
    0.28
     зави
    0.28
    σ
    0.28
    人民币
    0.27
     гро
    0.27
    𝓪
    0.27
     impossible
    0.26
     imposible
    0.26
     ['$
    0.26
    Activations Density 0.005%

    No Known Activations