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

    Neuronpedia

    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. 164247
    Prev
    Next
    INDEX
    Explanations

    preceding definitions or descriptions

    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
    ඓ
    0.38
    主人公
    0.38
     introduces
    0.38
     ডিম
    0.38
     $\{(
    0.37
    鲍
    0.37
     статистики
    0.36
    дового
    0.36
     تكلم
    0.35
    颌
    0.35
    POSITIVE LOGITS
     espaço
    0.39
    space
    0.38
    ْس
    0.38
     space
    0.37
     dirty
    0.36
     Shui
    0.36
    Dirty
    0.35
     ruimte
    0.35
     శి
    0.35
     waterproofing
    0.34
    Activations Density 0.000%

    No Known Activations