© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82539
    Prev
    Next
    INDEX
    Explanations

    list items or definitions

    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_29_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
    ಚ
    0.32
    ᄈ
    0.30
     फाउंड
    0.30
    ようだ
    0.30
     비해
    0.30
    盅
    0.30
    тивными
    0.29
    ラム
    0.29
     постепенно
    0.29
    骠
    0.29
    POSITIVE LOGITS
    absch
    0.34
     Ac
    0.33
    adora
    0.33
     this
    0.32
     Slice
    0.32
    aldas
    0.32
     daí
    0.32
    óa
    0.32
    oclonal
    0.31
    rocess
    0.31
    Activations Density 0.033%

    No Known Activations