© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53483
    Prev
    Next
    INDEX
    Explanations

    three

    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
     vier
    0.77
    四个
    0.74
     bốn
    0.73
    four
    0.71
    四
    0.69
     four
    0.68
    Four
    0.68
     cuatro
    0.67
     Four
    0.67
     quatro
    0.66
    POSITIVE LOGITS
    三
    1.26
     Three
    1.22
     三
    1.20
     three
    1.20
     THREE
    1.20
     الثلاث
    1.20
    Three
    1.19
    THREE
    1.17
     trois
    1.12
     трех
    1.12
    Activations Density 0.132%

    No Known Activations