© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155276
    Prev
    Next
    INDEX
    Explanations

    sun

    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_50_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
     Ila
    0.49
    ag
    0.44
     абстра
    0.42
    頰
    0.42
    列表中
    0.38
    esquerda
    0.38
    щ
    0.36
    edged
    0.35
     Ген
    0.35
    伫
    0.35
    POSITIVE LOGITS
    太阳
    0.57
    太陽
    0.55
     thái
    0.49
     tin
    0.47
     сле
    0.46
    Sunny
    0.44
     Sunny
    0.43
     solar
    0.43
    SUN
    0.43
    <0xAF>
    0.42
    Activations Density 0.009%

    No Known Activations