© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123641
    Prev
    Next
    INDEX
    Explanations

    compiler flags

    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_37_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
    Syntax
    0.55
     syntax
    0.46
     Syntax
    0.45
     démar
    0.45
    语法
    0.42
    SYN
    0.39
    绞
    0.38
    بح
    0.38
     lógico
    0.38
    Tahoma
    0.38
    POSITIVE LOGITS
     HD
    0.44
     एचडी
    0.40
     thistle
    0.36
     গোল
    0.36
     robust
    0.36
     Nets
    0.35
    明的
    0.35
    譜
    0.34
     दिखी
    0.34
     canonical
    0.34
    Activations Density 0.002%

    No Known Activations