© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 208950
    Prev
    Next
    INDEX
    Explanations

    safety ratings and tests

    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_20_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
    ชน์
    0.49
    enschutz
    0.48
     作詞
    0.48
     chimney
    0.48
    壤
    0.47
    මක්
    0.45
     patented
    0.45
    skcipher
    0.44
    onymous
    0.44
    ocket
    0.44
    POSITIVE LOGITS
     pobreza
    0.49
    官
    0.43
     pä
    0.41
     planète
    0.41
     vulner
    0.40
     Finances
    0.40
     vulnerability
    0.39
     amea
    0.39
    得意
    0.38
     Dealers
    0.38
    Activations Density 0.000%

    No Known Activations