© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44076
    Prev
    Next
    INDEX
    Explanations

    magic bullet

    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_3_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
    ेट
    0.67
    ने
    0.65
    ти
    0.64
    คุณ
    0.64
    गत
    0.63
    만
    0.62
    ian
    0.61
    ката
    0.61
     चुंबकीय
    0.60
    де
    0.60
    POSITIVE LOGITS
     procede
    0.77
    f
    0.77
     marzo
    0.69
    x
    0.68
     enfoque
    0.67
     varía
    0.66
     calendario
    0.65
    iciencia
    0.64
     ascol
    0.64
     creó
    0.63
    Activations Density 0.002%

    No Known Activations