© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214347
    Prev
    Next
    INDEX
    Explanations

    structured learning paths

    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_5_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
    ד
    1.47
    س
    1.41
    ל
    1.39
    ス
    1.27
    י
    1.22
    А
    1.16
    ルイ
    1.16
    Υ
    1.14
    Α
    1.13
    ম
    1.13
    POSITIVE LOGITS
    ियों
    1.75
    ých
    1.55
    ේ
    1.45
    ى
    1.43
    ين
    1.41
    ку
    1.37
    िक
    1.31
    ్య
    1.31
    ной
    1.30
    ных
    1.28
    Activations Density 0.005%

    No Known Activations