© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59423
    Prev
    Next
    INDEX
    Explanations

    at a high level

    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_2_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
    ه
    1.59
    س
    1.52
    ت
    1.36
    د
    1.34
     to
    1.33
    t
    1.26
    اً
    1.16
    行
    1.15
    ٩
    1.13
    。
    1.13
    POSITIVE LOGITS
    ING
    1.30
     I
    1.30
     accompl
    1.06
    ul
    1.05
     for
    0.99
     pentes
    0.98
     eğer
    0.97
    ERS
    0.96
     uomini
    0.95
    -
    0.94
    Activations Density 0.001%

    No Known Activations