© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198316
    Prev
    Next
    INDEX
    Explanations

    word problems with conditionals

    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_27_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
    летний
    0.39
     Carpet
    0.36
     Gén
    0.35
    ⌝
    0.34
     Detail
    0.34
     ⋅
    0.34
    курс
    0.34
    +"|
    0.33
     Safari
    0.33
     *$
    0.33
    POSITIVE LOGITS
    又
    0.43
    Dang
    0.43
    ắng
    0.40
    imony
    0.38
     उजा
    0.38
    Flowers
    0.38
    Doug
    0.37
    迥
    0.37
     доку
    0.36
     తీసుకోవ
    0.36
    Activations Density 0.001%

    No Known Activations