© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12436
    Prev
    Next
    INDEX
    Explanations

    average, mean, or median calculation

    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_13_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
    ation
    0.27
     साब
    0.25
    ien
    0.24
     श
    0.23
     იყო
    0.23
     तेल
    0.23
     excess
    0.23
    ↵
    0.23
    atically
    0.22
     ശേഷം
    0.22
    POSITIVE LOGITS
    平均
    0.26
    ων
    0.24
    сист
    0.23
     平均
    0.23
    줘
    0.22
    比较
    0.21
    ElapsedTime
    0.21
    denom
    0.21
    жу
    0.21
     Aver
    0.21
    Activations Density 0.052%

    No Known Activations