© 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. 194416
    Prev
    Next
    INDEX
    Explanations

    cereal, crisps, cakes, fluff, syrup

    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
    𝘬
    0.63
     defy
    0.55
    k
    0.53
    ul
    0.53
     Sam
    0.52
     c
    0.51
     Jang
    0.51
     hee
    0.51
     Punjab
    0.50
    um
    0.50
    POSITIVE LOGITS
     différences
    0.57
    而是
    0.53
    Debugger
    0.53
     ڈ
    0.52
     細胞
    0.52
     édition
    0.52
     الأخيرة
    0.52
    Genome
    0.52
     Unterschiede
    0.52
    ็
    0.52
    Activations Density 0.000%

    No Known Activations