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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33211
    Prev
    Next
    INDEX
    Explanations

    2

    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_31_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
    ліка
    0.38
    檛
    0.35
     kcal
    0.35
    BAC
    0.34
    当量
    0.33
    逐
    0.33
     bai
    0.32
    峄
    0.32
    DBD
    0.31
     kPa
    0.31
    POSITIVE LOGITS
     Brid
    0.38
     maturing
    0.36
     ಈಗಾಗಲೇ
    0.35
     Bowling
    0.35
    ørte
    0.34
     ఇప్పటికే
    0.34
    atrice
    0.34
     ALLE
    0.34
    ície
    0.33
    selectedIndex
    0.33
    Activations Density 0.017%

    No Known Activations