© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11449
    Prev
    Next
    INDEX
    Explanations

    to say the least

    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_13_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
    {
    0.57
    DB
    0.51
    ва
    0.49
    Present
    0.48
    Ornament
    0.47
    SD
    0.47
    ツール
    0.47
    ран
    0.47
    ራ
    0.47
    ロ
    0.47
    POSITIVE LOGITS
     зміню
    0.56
     adequado
    0.54
     headline
    0.52
    ელია
    0.51
     admissions
    0.51
     recevoir
    0.51
     sustain
    0.50
     disparity
    0.50
     geçir
    0.50
     superpower
    0.50
    Activations Density 0.004%

    No Known Activations