© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195247
    Prev
    Next
    INDEX
    Explanations

    colour optimisation behaviour

    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_15_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
    s
    0.47
    ד
    0.43
    -
    0.42
     at
    0.42
     to
    0.42
     has
    0.41
     bisogno
    0.41
    ים
    0.41
     were
    0.39
     amante
    0.38
    POSITIVE LOGITS
     그러나
    0.50
     однако
    0.49
    ায়ক
    0.46
     డ
    0.45
     అన్ని
    0.45
     लेकिन
    0.43
    Colour
    0.43
    但是
    0.43
     ആദ്യ
    0.43
     ਅਤੇ
    0.42
    Activations Density 0.019%

    No Known Activations