© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152654
    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_23_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
    و
    0.52
    ocr
    0.44
    develop
    0.44
    ک
    0.44
    目の
    0.43
    ूहिक
    0.41
     Mérida
    0.41
    山上
    0.41
    declar
    0.40
     prevenção
    0.40
    POSITIVE LOGITS
    পা
    0.48
     accentuated
    0.48
     Broughton
    0.48
     puck
    0.47
    ্চ
    0.45
    깃
    0.45
     Grenzen
    0.44
    aikh
    0.44
     nevertheless
    0.44
     berichtet
    0.44
    Activations Density 0.000%

    No Known Activations