© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43156
    Prev
    Next
    INDEX
    Explanations

    degrees and fields of study

    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
    ysk
    0.45
    u
    0.43
    ust
    0.39
    up
    0.39
    ier
    0.39
    matched
    0.39
    surname
    0.39
    yskland
    0.39
     family
    0.38
    wyn
    0.38
    POSITIVE LOGITS
     рынок
    0.58
     Н
    0.56
     кило
    0.55
     н
    0.55
     её
    0.54
    ఎల్
    0.53
     ее
    0.52
     ядер
    0.52
    ಎಂ
    0.52
    ịp
    0.52
    Activations Density 0.003%

    No Known Activations