© 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. 78198
    Prev
    Next
    INDEX
    Explanations

    Di

    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
    眎
    0.42
    uraea
    0.40
    ExternalTaskPojo
    0.39
    ቷ
    0.38
    Khokhlov
    0.37
    ផ្
    0.35
    ﾈ
    0.35
     fontstyle
    0.35
    Pb
    0.35
     Subaru
    0.34
    POSITIVE LOGITS
     Ди
    2.19
     ди
    1.97
    Ди
    1.91
    ディ
    1.85
     디
    1.81
     ディ
    1.77
    ди
    1.71
    디
    1.71
     Dí
    1.65
    Dic
    1.63
    Activations Density 0.000%

    No Known Activations