© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59526
    Prev
    Next
    INDEX
    Explanations

    appendix references

    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_11_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
    r
    0.59
    kv
    0.55
    ینے
    0.54
    x
    0.52
    Ҡ
    0.52
    垮
    0.52
    ppen
    0.51
    peau
    0.50
     heralded
    0.50
    یوں
    0.50
    POSITIVE LOGITS
    \
    0.64
         
    0.61
     complète
    0.60
    та
    0.59
     podrá
    0.58
     Pued
    0.57
    -
    0.57
     informacije
    0.57
    ट्र
    0.56
     toner
    0.55
    Activations Density 0.000%

    No Known Activations