© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215586
    Prev
    Next
    INDEX
    Explanations

    code formatting symbols

    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_31_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
     درد
    0.38
     समर्पित
    0.38
    coder
    0.38
    玥
    0.38
    贖
    0.38
     తెర
    0.37
    軹
    0.36
    借鉴
    0.35
     Kodak
    0.35
    限界
    0.35
    POSITIVE LOGITS
     milling
    0.40
    ונה
    0.36
     pottery
    0.36
     ziy
    0.36
    umbres
    0.35
     ")[
    0.34
    เนื้อ
    0.34
    場合がございます
    0.34
     hept
    0.34
     bistro
    0.34
    Activations Density 0.000%

    No Known Activations