© 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. 44927
    Prev
    Next
    INDEX
    Explanations

    process

    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
    0
    0.69
    #.
    0.63
    ६
    0.63
    www
    0.62
    1
    0.61
     heutigen
    0.60
    antly
    0.59
    rives
    0.59
    ｈ
    0.58
    λλ
    0.57
    POSITIVE LOGITS
    मैन
    0.75
     PRO
    0.73
     ú
    0.73
     paramet
    0.72
     perde
    0.70
     có
    0.69
     pré
    0.68
     agu
    0.68
     Aprend
    0.68
     nej
    0.68
    Activations Density 0.003%

    No Known Activations