© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138937
    Prev
    Next
    INDEX
    Explanations

    7th, 6th

    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
    یاط
    0.40
     backed
    0.39
    }+(
    0.39
    isions
    0.38
     revel
    0.37
    ัญ
    0.37
    icha
    0.37
     avert
    0.37
    湁
    0.36
    utherland
    0.34
    POSITIVE LOGITS
     PRODUCTS
    0.39
    ಂ
    0.38
    வான்
    0.38
     ప్రాంత
    0.37
     제품
    0.36
     Manik
    0.36
    ਜੀ
    0.35
     عشر
    0.35
     commencer
    0.34
    Flask
    0.34
    Activations Density 0.000%

    No Known Activations