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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228730
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    يم
    0.47
    сну
    0.46
    𝑆
    0.44
     тог
    0.40
     স্টে
    0.40
    िटेशन
    0.40
    Fridge
    0.39
    প্তরের
    0.39
     сани
    0.39
    шой
    0.39
    POSITIVE LOGITS
     ele
    0.44
     بز
    0.43
     nad
    0.43
     ка
    0.42
     eld
    0.41
    Ele
    0.41
     Ele
    0.40
     e
    0.39
     ka
    0.39
     eighty
    0.38
    Activations Density 0.001%

    No Known Activations