© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131603
    Prev
    Next
    INDEX
    Explanations

    Arabic, English, Thai, Ukrainian, Vietnamese, Italian, Russian, Pashto, Kannada, Turkish, Malayalam, punctuation

    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_1_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
    ↵
    1.80
    1
    1.66
    In
    1.49
    4
    1.49
    6
    1.47
    大
    1.44
    5
    1.41
    ↵↵
    1.41
    .
    1.37
    A
    1.37
    POSITIVE LOGITS
     quá
    1.34
     لوبو
    1.33
     جوړونک
    1.17
     modificare
    1.17
     від
    1.11
     відповіда
    1.11
     вновь
    1.10
     ລັບ
    1.10
     discouraged
    1.09
     về
    1.08
    Activations Density 0.000%

    No Known Activations