© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131628
    Prev
    Next
    INDEX
    Explanations

    most notably

    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_1_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
    م
    1.31
    м
    1.28
     legitim
    1.27
     principales
    1.13
     horario
    1.13
    К
    1.13
     grandes
    1.11
    ОР
    1.11
    يل
    1.10
     importantes
    1.09
    POSITIVE LOGITS
    dale
    1.05
    al
    1.05
     can
    1.02
    ۰
    0.93
    o
    0.91
    с
    0.87
     жана
    0.86
    ি
    0.86
    I
    0.85
    gradient
    0.83
    Activations Density 0.000%

    No Known Activations