© 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. 42550
    Prev
    Next
    INDEX
    Explanations

    ryabhata, Grande, Ariane, Kaplan

    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
    T
    0.73
    M
    0.68
    いますが
    0.66
    L
    0.63
    R
    0.63
    K
    0.62
    an
    0.62
    P
    0.62
    Z
    0.62
    و
    0.61
    POSITIVE LOGITS
     enhancers
    0.72
    isatie
    0.71
     effluents
    0.70
     ét
    0.65
     terminado
    0.64
     finales
    0.63
     is
    0.63
     científicos
    0.62
     आने
    0.62
    ンテ
    0.61
    Activations Density 0.000%

    No Known Activations