© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214116
    Prev
    Next
    INDEX
    Explanations

    evolves

    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_5_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
    ל
    1.27
    ER
    1.18
    ج
    1.15
    ב
    1.15
    ↵
    1.13
     Peking
    1.05
    ร
    1.03
     riche
    1.02
    ر
    0.99
     lokalen
    0.99
    POSITIVE LOGITS
    n
    1.56
    1
    1.52
    t
    1.41
    ки
    1.34
    é
    1.30
    ag
    1.28
    ang
    1.27
    ert
    1.27
    iz
    1.26
    ell
    1.24
    Activations Density 0.002%

    No Known Activations