© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47316
    Prev
    Next
    INDEX
    Explanations

    chip series designations

    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_10_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
     l
    0.91
     R
    0.89
    l
    0.84
    i
    0.81
     P
    0.80
    an
    0.79
     C
    0.79
     F
    0.75
     E
    0.75
     B
    0.73
    POSITIVE LOGITS
    نې
    0.75
    پے
    0.70
    LineWidth
    0.67
     sasane
    0.66
     aswell
    0.66
    InterfaceLine
    0.66
    禰
    0.66
    Ⲱ
    0.65
    羍
    0.65
     کرکے
    0.64
    Activations Density 0.009%

    No Known Activations