© 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. 43888
    Prev
    Next
    INDEX
    Explanations

    Bellweather

    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
    ى
    0.75
     I
    0.69
     can
    0.66
    (
    0.61
    ете
    0.59
    c
    0.59
    ía
    0.58
    t
    0.57
    ە
    0.57
    ع
    0.57
    POSITIVE LOGITS
    ))
    0.83
    ്ല
    0.68
    EL
    0.68
    ги
    0.67
    UR
    0.66
     रोगों
    0.66
    AK
    0.65
    ि
    0.64
    गा
    0.64
    he
    0.63
    Activations Density 0.000%

    No Known Activations