© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200117
    Prev
    Next
    INDEX
    Explanations

    webpack configuration plugins

    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_12_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
    curvature
    0.46
    addies
    0.43
     архівів
    0.43
    𝘦
    0.41
     chiều
    0.41
     만
    0.40
    獼
    0.40
     다만
    0.39
     कामया
    0.39
    sensitivity
    0.38
    POSITIVE LOGITS
    ण्याचा
    0.41
     f
    0.39
     Island
    0.38
    ób
    0.38
    っている
    0.37
    리오
    0.37
    anor
    0.37
    5
    0.37
    ón
    0.37
     incompetent
    0.37
    Activations Density 0.001%

    No Known Activations