© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208781
    Prev
    Next
    INDEX
    Explanations

    quantity or number ranges

    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_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
     Ам
    0.24
     Nikhil
    0.24
    yam
    0.23
     Κα
    0.23
     Κ
    0.22
     Σ
    0.21
     Ben
    0.21
     Αν
    0.21
     Τ
    0.20
     少し
    0.20
    POSITIVE LOGITS
     ony
    0.24
     auc
    0.23
     roughly
    0.23
     approximately
    0.22
     reclam
    0.22
     acar
    0.22
     desn
    0.22
     çoğu
    0.22
     sering
    0.21
     flora
    0.21
    Activations Density 0.002%

    No Known Activations