© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14108
    Prev
    Next
    INDEX
    Explanations

    CAD, CHF, Canada

    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_40_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
    Class
    0.45
     убе
    0.43
     Class
    0.40
    艐
    0.39
     언
    0.38
    cnc
    0.38
     그린
    0.37
    Kelas
    0.37
    아버지
    0.37
    arc
    0.36
    POSITIVE LOGITS
     made
    0.54
    密封
    0.45
    陝
    0.43
     sounded
    0.42
     MADE
    0.42
     adecu
    0.41
     CHINA
    0.39
     फ्ल
    0.39
    made
    0.39
     Made
    0.39
    Activations Density 0.000%

    No Known Activations