© 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. 76197
    Prev
    Next
    INDEX
    Explanations

    shipping and delivery methods

    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
     деревя
    0.37
    ستہ
    0.36
    %+
    0.36
     wood
    0.36
    ematic
    0.35
     smoked
    0.34
     Cann
    0.34
     धना
    0.34
     инсу
    0.34
    %,
    0.33
    POSITIVE LOGITS
    िकास
    0.39
    Microsoft
    0.39
    purse
    0.39
    PixelRatio
    0.38
    scaping
    0.38
    奔驰
    0.38
    pOt
    0.38
     جهانی
    0.37
    galax
    0.37
     عالم
    0.37
    Activations Density 0.000%

    No Known Activations