© 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. 143224
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ធ
    0.41
    拨
    0.41
    оборот
    0.41
     따라서
    0.41
     rupture
    0.41
     breakout
    0.40
     endDate
    0.39
    ্যান্ড
    0.39
     Tul
    0.39
     toler
    0.38
    POSITIVE LOGITS
     Kirsten
    0.40
     airing
    0.37
    險
    0.37
    রীণ
    0.36
     अंग्रे
    0.35
     GALL
    0.34
     calci
    0.34
     Jenn
    0.33
    英語
    0.33
    gad
    0.33
    Activations Density 0.000%

    No Known Activations