© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45135
    Prev
    Next
    INDEX
    Explanations

    MinIO, Mineplex, Minkowski Space

    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
    i
    0.85
    y
    0.77
    a
    0.74
    e
    0.72
    ed
    0.67
    at
    0.64
        
    0.63
    ið
    0.62
    ي
    0.61
    er
    0.61
    POSITIVE LOGITS
    ২
    0.66
     destinados
    0.66
    ш
    0.65
    ä
    0.62
    ści
    0.60
     periódico
    0.60
     człon
    0.59
     partidos
    0.58
     retiro
    0.56
    <0x0D>
    0.55
    Activations Density 0.001%

    No Known Activations