© 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. 229410
    Prev
    Next
    INDEX
    Explanations

    from

    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
    وط
    0.50
    ню
    0.45
    𝑛
    0.40
     thiện
    0.39
    ня
    0.38
    ра
    0.37
     عدم
    0.37
    Applicant
    0.37
    legen
    0.36
     plotted
    0.36
    POSITIVE LOGITS
    تع
    0.45
    గ
    0.39
    đu
    0.37
    Tech
    0.37
    arant
    0.35
    衝
    0.34
    шел
    0.34
    تق
    0.34
     violates
    0.33
    đe
    0.33
    Activations Density 0.002%

    No Known Activations