© 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. 235649
    Prev
    Next
    INDEX
    Explanations

    Japanese syllables

    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
     Edo
    0.45
     मेघा
    0.41
     Heck
    0.40
     TEXAS
    0.39
     HW
    0.39
     گی۔
    0.39
    Led
    0.38
     $('<
    0.38
     pk
    0.38
    icea
    0.38
    POSITIVE LOGITS
     sh
    0.90
     Sh
    0.81
     fut
    0.78
     tat
    0.77
    Sh
    0.71
     Shin
    0.70
    Tat
    0.64
     Fut
    0.63
     Tat
    0.62
     ش
    0.61
    Activations Density 0.001%

    No Known Activations