© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78579
    Prev
    Next
    INDEX
    Explanations

    Bengali, Korean, Japanese, Italian, German, English characters

    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_29_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
     wel
    0.41
     fortunes
    0.39
     f
    0.38
    culares
    0.37
    ARR
    0.37
     escudo
    0.36
    RIS
    0.35
     free
    0.35
    attutto
    0.35
    ंजक
    0.35
    POSITIVE LOGITS
    veys
    0.40
    🔸
    0.39
     ഗെയി
    0.37
    埛
    0.37
     গাছ
    0.36
     Италия
    0.36
    쩡
    0.36
    መሳሳይ
    0.35
     छात्रा
    0.35
     McCorm
    0.35
    Activations Density 0.007%

    No Known Activations