© 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. 78191
    Prev
    Next
    INDEX
    Explanations

    dhi hi

    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
    טו
    0.39
     মর
    0.38
    бран
    0.38
    識
    0.36
    ائدة
    0.35
    ನ್ನ
    0.34
    स्तानी
    0.34
    ান্ট
    0.34
     hag
    0.34
    ஹா
    0.34
    POSITIVE LOGITS
    ಧಿ
    0.76
    adhi
    0.66
    தி
    0.65
    ధి
    0.64
    ધ
    0.64
    ਧੀ
    0.62
    ധി
    0.60
    धी
    0.59
    提
    0.58
    HI
    0.58
    Activations Density 0.000%

    No Known Activations