© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59238
    Prev
    Next
    INDEX
    Explanations

    company profile

    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_11_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
     Rasa
    0.61
     aru
    0.60
     Nb
    0.60
     ary
    0.59
     ща
    0.58
    ƅ
    0.57
     inay
    0.56
     riscos
    0.56
     rischi
    0.55
     effetto
    0.54
    POSITIVE LOGITS
    r
    0.65
    re
    0.63
    de
    0.62
    ने
    0.61
    t
    0.57
    EN
    0.55
    Information
    0.54
    ETA
    0.54
    Assertion
    0.54
    Knowledge
    0.54
    Activations Density 0.000%

    No Known Activations