© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42728
    Prev
    Next
    INDEX
    Explanations

    Thousand Island dressing

    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_13_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
     reiniciar
    0.51
    guru
    0.50
    ənd
    0.48
     Pea
    0.48
    ,+
    0.47
     Fukushima
    0.47
     desn
    0.47
     EDU
    0.47
     एमसी
    0.47
     STAN
    0.47
    POSITIVE LOGITS
     botao
    0.55
     rowing
    0.55
    麝
    0.54
     ях
    0.52
     steamers
    0.51
    amatan
    0.50
     cholinergic
    0.50
     boating
    0.50
     sahabat
    0.50
    航
    0.49
    Activations Density 0.000%

    No Known Activations