© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9761
    Prev
    Next
    INDEX
    Explanations

    react and mui components

    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_40_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
    торию
    0.42
     Rund
    0.41
    禟
    0.41
    legten
    0.39
    beschreibung
    0.39
    يًا
    0.38
    jia
    0.37
    মালা
    0.36
    ردم
    0.36
    ային
    0.36
    POSITIVE LOGITS
     slate
    0.40
     fift
    0.39
    测
    0.39
    UserService
    0.38
     userService
    0.38
     fade
    0.37
    是多少
    0.37
     dual
    0.37
     mongoose
    0.37
     height
    0.36
    Activations Density 0.002%

    No Known Activations