© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37293
    Prev
    Next
    INDEX
    Explanations

    analyzing data structures

    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
    名
    0.38
     khẩu
    0.35
     விஷ
    0.35
    เม
    0.34
    ыргыз
    0.34
    مه
    0.33
    名の
    0.33
    입
    0.33
     ని
    0.32
    куси
    0.32
    POSITIVE LOGITS
    ⣤
    0.38
     قم
    0.35
    𝗩
    0.35
    𝕊
    0.34
    oodle
    0.34
    ḷ
    0.33
     Mosc
    0.33
     Ando
    0.33
    ={$
    0.33
    ꜱ
    0.33
    Activations Density 0.021%

    No Known Activations