© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239054
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    =(
    0.10
     tracker
    0.09
     detector
    0.09
    жены
    0.09
    tracker
    0.08
    =
    0.08
    زمة
    0.08
    的其他
    0.08
     depart
    0.08
    ===
    0.08
    POSITIVE LOGITS
     Pilates
    0.10
    হেল
    0.09
     tuttavia
    0.09
     परन्तु
    0.09
     துன்ப
    0.09
     ужа
    0.09
    ंबित
    0.09
     faux
    0.09
     ಭಯ
    0.09
     Induced
    0.08
    Activations Density 0.000%

    No Known Activations