© 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. 125370
    Prev
    Next
    INDEX
    Explanations

    clinical trials, life, beatbox, bao

    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
    ٦
    0.71
     droite
    0.67
     diminuer
    0.64
     frecuente
    0.63
     certificat
    0.63
     едно
    0.62
     tener
    0.62
     cinque
    0.62
    <0xBF>
    0.60
    ６
    0.59
    POSITIVE LOGITS
    t
    0.97
    2
    0.87
    л
    0.79
     is
    0.78
    ل
    0.74
    ק
    0.71
    d
    0.71
    ر
    0.68
    स
    0.64
    z
    0.64
    Activations Density 0.001%

    No Known Activations