© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84540
    Prev
    Next
    INDEX
    Explanations

    free copy, code, SD card

    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_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
    汙
    0.40
    少し
    0.38
     少し
    0.38
    友情
    0.38
    चाल
    0.37
     rolled
    0.37
     प्रशासन
    0.37
    ｴ
    0.37
    ps
    0.37
    ूल
    0.37
    POSITIVE LOGITS
    iduría
    0.46
    ꯟ
    0.44
     Vestone
    0.43
     Fernanda
    0.41
     vektor
    0.40
     desactiv
    0.40
    ləşdir
    0.40
     पाओ
    0.40
     ¿?
    0.39
     factorizar
    0.39
    Activations Density 0.000%

    No Known Activations