© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82716
    Prev
    Next
    INDEX
    Explanations

    foreign language/symbols

    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_53_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
    IC
    0.39
     ACC
    0.39
    ป
    0.38
     Ș
    0.37
     Рассмотрим
    0.37
     أخ
    0.36
    IM
    0.36
     HID
    0.36
    Ķ
    0.36
    AC
    0.35
    POSITIVE LOGITS
     فَ
    0.46
     fie
    0.39
    !!!!!!
    0.39
     عَ
    0.39
     ПРО
    0.37
    !!!!!!!
    0.37
     وَ
    0.36
    َہ
    0.36
     objecting
    0.35
     НЕ
    0.35
    Activations Density 0.185%

    No Known Activations