© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14351
    Prev
    Next
    INDEX
    Explanations

    so [adjective]

    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_13_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
    о
    0.54
    언
    0.52
     ㅇ
    0.51
    ス
    0.47
    よりも
    0.46
    тья
    0.46
    もっと
    0.45
    オ
    0.45
    이야
    0.44
    之間的
    0.43
    POSITIVE LOGITS
    fficient
    0.58
    ceans
    0.55
    oring
    0.54
    fly
    0.54
    ormal
    0.52
    requency
    0.49
    eni
    0.47
    ening
    0.47
    ce
    0.46
    adese
    0.46
    Activations Density 0.012%

    No Known Activations