© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108730
    Prev
    Next
    INDEX
    Explanations

    light in different languages

    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_2_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
    a
    1.63
    т
    1.62
    า
    1.53
    ून
    1.52
    ン
    1.45
    is
    1.45
    ن
    1.40
    Light
    1.38
    isn
    1.36
    د
    1.34
    POSITIVE LOGITS
    ط
    1.02
    يل
    0.91
    ς
    0.90
    <0x91>
    0.87
     relentless
    0.84
     diabetes
    0.83
    진다
    0.82
    ের
    0.82
     οποίο
    0.80
    ओं
    0.79
    Activations Density 0.001%

    No Known Activations