© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239081
    Prev
    Next
    INDEX
    Explanations

    .org websites

    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_25_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
    ெல்ல
    0.39
    国家
    0.37
    োঁ
    0.35
     शास्त्र
    0.34
    불
    0.34
     carreira
    0.34
     neuronal
    0.33
    스타그램
    0.33
    ÍT
    0.33
     국가
    0.33
    POSITIVE LOGITS
     Bradford
    0.44
    僅
    0.43
     മണ്ണി
    0.40
    ום
    0.39
    Utilization
    0.39
     Known
    0.39
     reaffirm
    0.38
     unwavering
    0.38
     Reg
    0.38
    াহার
    0.38
    Activations Density 0.003%

    No Known Activations