© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142836
    Prev
    Next
    INDEX
    Explanations

    both

    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_46_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
     Plusieurs
    0.36
    ayscale
    0.35
    ះ
    0.35
    usen
    0.35
    Ⲱ
    0.35
    iooni
    0.34
     Приступљено
    0.33
    ᑯ
    0.33
    CLC
    0.32
    nze
    0.32
    POSITIVE LOGITS
     both
    3.59
    both
    3.34
    Both
    3.09
     Both
    3.08
     BOTH
    2.83
     både
    2.67
    BOTH
    2.67
     दोनों
    2.64
     cả
    2.64
    ทั้ง
    2.61
    Activations Density 0.236%

    No Known Activations