© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81772
    Prev
    Next
    INDEX
    Explanations

    5

    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_53_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
    White
    1.80
     White
    1.78
     WHITE
    1.59
    white
    1.55
     white
    1.54
    WHITE
    1.51
    ホワイト
    1.43
    白
    1.32
     व्हाइट
    1.30
    白色
    1.19
    POSITIVE LOGITS
    cyj
    0.40
    娘
    0.36
    ận
    0.35
    জর
    0.35
    SessionFactory
    0.35
     約
    0.34
    టికి
    0.34
    履歴
    0.33
    Sono
    0.33
    嗳
    0.33
    Activations Density 0.003%

    No Known Activations