© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121366
    Prev
    Next
    INDEX
    Explanations

    Thai, Chinese, Greek, Bengali, Tamil, Pashto, English words

    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_38_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
     жизнь
    0.42
    leding
    0.40
    life
    0.39
     सं
    0.38
     fag
    0.38
    득
    0.38
     जुगा
    0.38
     जिंदगी
    0.38
     شاب
    0.37
     baba
    0.37
    POSITIVE LOGITS
     একত্র
    0.42
    骐
    0.42
     څرنګ
    0.40
    妫
    0.37
    Castle
    0.37
    ிய
    0.37
    Ꮘ
    0.36
    ")%>%
    0.35
    мию
    0.35
    俎
    0.35
    Activations Density 0.007%

    No Known Activations