© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49175
    Prev
    Next
    INDEX
    Explanations

    if, if, if

    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_31_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
    sentation
    0.41
    穎
    0.38
    ifferent
    0.38
    しっかりと
    0.37
    是否存在
    0.37
     pizarra
    0.36
     없이
    0.36
    different
    0.36
     Prey
    0.36
    ⅛
    0.36
    POSITIVE LOGITS
     requires
    0.41
    的话
    0.37
    Requires
    0.36
     अवश्य
    0.36
     certainly
    0.36
    requires
    0.36
     ain
    0.36
     فإن
    0.35
    则是
    0.35
    manın
    0.35
    Activations Density 0.039%

    No Known Activations