© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132705
    Prev
    Next
    INDEX
    Explanations

    punctuation"""

    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
     N
    0.47
    ्रल
    0.45
     الن
    0.44
    পে
    0.39
     reinterpret
    0.39
     rein
    0.38
     hine
    0.38
    N
    0.37
    reinterpret
    0.37
    iax
    0.36
    POSITIVE LOGITS
     பாதி
    0.41
    ყოფ
    0.41
    workbook
    0.41
    ೯
    0.39
    혀
    0.38
     chromos
    0.38
     प्रदूषण
    0.37
    Chromosome
    0.37
    ibilidades
    0.37
     Langer
    0.37
    Activations Density 0.000%

    No Known Activations