© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197501
    Prev
    Next
    INDEX
    Explanations

    minimization

    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_50_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
    yan
    0.45
     мес
    0.40
    iyan
    0.39
     Draw
    0.38
     अनिल
    0.38
    idikan
    0.37
    C
    0.37
     Ab
    0.37
    Jan
    0.37
     الكل
    0.37
    POSITIVE LOGITS
    तिम
    0.39
    ুনা
    0.38
    úa
    0.37
     ጋር
    0.35
    ارية
    0.35
    _='
    0.35
     spacers
    0.35
    riere
    0.35
    ocortic
    0.34
    ссмо
    0.34
    Activations Density 0.001%

    No Known Activations