© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36942
    Prev
    Next
    INDEX
    Explanations

    Qualcomm

    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_3_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
     món
    0.64
     недели
    0.59
    рт
    0.56
    нче
    0.55
    ৯
    0.55
    نة
    0.55
    슨
    0.55
    arın
    0.54
     ITA
    0.54
    كية
    0.54
    POSITIVE LOGITS
    is
    0.71
    ра
    0.67
    ри
    0.64
    }.
    0.63
     fresca
    0.61
    ד
    0.59
    a
    0.57
    ні
    0.57
     μεγάλη
    0.57
    aft
    0.57
    Activations Density 0.014%

    No Known Activations