© 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. 89631
    Prev
    Next
    INDEX
    Explanations

    version numbers from package installs

    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
    にとっては
    0.44
     شناخت
    0.38
     előtt
    0.38
    ƅ
    0.37
    ھا
    0.37
     சென்ன
    0.37
    ）：
    0.36
     benar
    0.36
    alanine
    0.36
     બંધ
    0.36
    POSITIVE LOGITS
    Listo
    0.39
    JR
    0.39
     LJ
    0.36
    ologija
    0.36
    罰
    0.36
    电视台
    0.36
     igualmente
    0.35
    HttpResponse
    0.35
    Jersey
    0.35
    Catagory
    0.35
    Activations Density 0.000%

    No Known Activations