© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49948
    Prev
    Next
    INDEX
    Explanations

    broken, rusted, rock

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     C
    1.81
    C
    1.58
     الص
    1.32
    setC
    1.07
     הצ
    0.88
     सी
    0.81
    getC
    0.79
    الص
    0.79
     ค
    0.77
    Ｃ
    0.70
    POSITIVE LOGITS
    b
    0.60
     B
    0.51
     الب
    0.41
     Б
    0.40
    faithful
    0.40
    работка
    0.38
     הב
    0.37
    બ
    0.36
    侔
    0.36
     griev
    0.35
    Activations Density 0.064%

    No Known Activations