© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107943
    Prev
    Next
    INDEX
    Explanations

    for instance,

    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_1_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
    it
    1.12
     it
    1.10
    ال
    1.09
    사
    1.06
    ”
    1.05
    ’
    1.04
    D
    1.02
    G
    1.02
    ل
    1.01
    ট
    1.00
    POSITIVE LOGITS
     في
    1.09
    y
    0.95
     прове
    0.93
    BackgroundHelper
    0.89
    á
    0.86
     достига
    0.85
     който
    0.85
    1
    0.84
     σε
    0.84
     كه
    0.83
    Activations Density 0.000%

    No Known Activations