© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140049
    Prev
    Next
    INDEX
    Explanations

    Navratri, nights, goddess, dance, Gujarat

    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_12_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
    澜
    0.54
     obrá
    0.54
    டன்
    0.52
    ленных
    0.52
     hsize
    0.52
     evanescent
    0.50
     गया
    0.50
     parecer
    0.50
     alcance
    0.49
     }(
    0.49
    POSITIVE LOGITS
    support
    0.59
    ting
    0.58
    ships
    0.58
    ad
    0.57
    ts
    0.57
    ub
    0.54
    ments
    0.53
    t
    0.53
    taining
    0.50
    swick
    0.50
    Activations Density 0.000%

    No Known Activations