© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41944
    Prev
    Next
    INDEX
    Explanations

    programming keywords or database columns

    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_22_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
    ">=</
    0.40
    ехать
    0.39
    зяй
    0.38
     =\
    0.38
    ikut
    0.38
     (=
    0.38
    痉
    0.37
     glLightfv
    0.37
    污
    0.37
     บ้าน
    0.36
    POSITIVE LOGITS
    ær
    0.45
     prenez
    0.43
     Martin
    0.42
    Martin
    0.41
    Você
    0.41
     মার্ট
    0.41
     knobs
    0.41
     जॉ
    0.40
    package
    0.39
    ons
    0.39
    Activations Density 0.000%

    No Known Activations