© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101981
    Prev
    Next
    INDEX
    Explanations

    quality standards

    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_14_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
     leurs
    0.68
     م
    0.59
     जास्त
    0.57
     kanilang
    0.55
    itivos
    0.55
     criou
    0.55
     чёр
    0.54
     muita
    0.54
     mensagens
    0.54
     leur
    0.53
    POSITIVE LOGITS
    o
    0.57
    endswith
    0.53
    amples
    0.50
     Tarn
    0.50
    dering
    0.50
    AA
    0.49
    na
    0.49
    Dock
    0.49
     ocz
    0.49
    (['
    0.49
    Activations Density 0.000%

    No Known Activations