© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130044
    Prev
    Next
    INDEX
    Explanations

    real-valued or theoretic concepts

    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_6_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
    9
    1.08
    5
    1.05
    しております
    0.85
    6
    0.85
    रिक्त
    0.80
     испыта
    0.78
     veliko
    0.77
     экзем
    0.77
    8
    0.76
     обеспечение
    0.75
    POSITIVE LOGITS
     in
    1.46
    g
    1.29
    h
    1.24
    在
    1.19
    s
    1.02
    u
    1.02
    in
    1.00
    k
    0.98
    t
    0.96
    ใน
    0.91
    Activations Density 0.001%

    No Known Activations