© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104952
    Prev
    Next
    INDEX
    Explanations

    photorealistic hyperrealism

    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_1_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
    ت
    1.87
    ب
    1.52
    y
    1.45
    t
    1.40
    ב
    1.39
    ع
    1.35
    т
    1.33
    는
    1.28
    य
    1.23
    ?
    1.23
    POSITIVE LOGITS
     மன்ற
    0.90
    も
    0.87
    cknowled
    0.85
    логии
    0.83
     for
    0.82
    dg
    0.82
    for
    0.81
    じて
    0.81
    ة
    0.81
    entwick
    0.80
    Activations Density 0.000%

    No Known Activations