© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199008
    Prev
    Next
    INDEX
    Explanations

    mixed context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     след
    0.39
     urme
    0.38
     vif
    0.36
    ﺷ
    0.36
     Greene
    0.36
    鿌
    0.36
     специфи
    0.35
     vat
    0.35
    ेटा
    0.35
    catch
    0.35
    POSITIVE LOGITS
     spilling
    0.40
    ংকার
    0.36
     разли
    0.36
    thai
    0.36
    ointers
    0.36
    Dict
    0.35
    ylabel
    0.35
     Dict
    0.35
    协调
    0.35
    宙
    0.35
    Activations Density 0.002%

    No Known Activations