© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76949
    Prev
    Next
    INDEX
    Explanations

    crafting and designs

    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
     Handbook
    0.39
    Bismillahirrah
    0.38
    Handbook
    0.37
    Materials
    0.37
     कढ़ाई
    0.35
     handbook
    0.35
    筅
    0.34
     knitted
    0.34
     Himmel
    0.34
     Materials
    0.34
    POSITIVE LOGITS
    ObjectUnderTest
    0.38
    補充
    0.34
    மன்
    0.32
     程
    0.32
     Freddy
    0.31
    字体
    0.30
     Sanjay
    0.30
     چال
    0.30
     πε
    0.30
    补充
    0.30
    Activations Density 0.003%

    No Known Activations