© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79773
    Prev
    Next
    INDEX
    Explanations

    optimal strategy or outcome

    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_0_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
    to
    2.39
    in
    1.88
    u
    1.84
    ו
    1.73
     to
    1.55
    า
    1.52
    ो
    1.50
    at
    1.48
    ра
    1.45
    as
    1.34
    POSITIVE LOGITS
    కు
    1.93
    是
    1.86
    هاي
    1.65
    ني
    1.63
    كي
    1.63
    ون
    1.54
    ના
    1.53
    는
    1.52
    は
    1.50
    (
    1.48
    Activations Density 0.001%

    No Known Activations