© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199998
    Prev
    Next
    INDEX
    Explanations

    six

    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_46_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
     dua
    0.48
     двух
    0.47
    ული
    0.45
     இரண்டு
    0.44
    두
    0.44
     deux
    0.43
     duas
    0.43
     zwei
    0.42
     Deux
    0.41
     dois
    0.41
    POSITIVE LOGITS
    Anthony
    0.56
     Anthony
    0.51
    ៦
    0.49
    6
    0.48
    ６
    0.44
     Six
    0.43
     Sixth
    0.43
     ۶
    0.43
     Ear
    0.41
    Sixth
    0.40
    Activations Density 0.030%

    No Known Activations