© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14130
    Prev
    Next
    INDEX
    Explanations

    provides a solution

    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_15_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
    ॉक
    0.54
     Theater
    0.54
    再
    0.50
    ার্জ
    0.50
    会社
    0.50
     Recon
    0.49
    从
    0.49
     Search
    0.48
     Übers
    0.48
     Authent
    0.48
    POSITIVE LOGITS
    eleration
    0.56
    :\
    0.56
     malaise
    0.55
    annulation
    0.55
    畂
    0.54
     ino
    0.51
     chén
    0.50
     indifference
    0.49
     enteros
    0.49
    oru
    0.49
    Activations Density 0.003%

    No Known Activations