© 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. 36361
    Prev
    Next
    INDEX
    Explanations

    within the

    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
    +\
    0.82
    𝑠
    0.82
    魑
    0.79
    миз
    0.75
    𝑖
    0.73
    _{(\
    0.71
    ıları
    0.70
     equilíbrio
    0.69
    ()\
    0.69
    on
    0.68
    POSITIVE LOGITS
    I
    0.83
     ።
    0.74
     。
    0.70
    。
    0.68
    0.68
    D
    0.65
    be
    0.64
    ร
    0.62
    ។
    0.61
     sayf
    0.60
    Activations Density 0.010%

    No Known Activations