© 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. 58525
    Prev
    Next
    INDEX
    Explanations

    next comes

    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
    ু
    1.66
    ೇ
    1.56
    ه
    1.52
    us
    1.49
    ు
    1.46
    ל
    1.45
    تي
    1.42
    is
    1.41
    ي
    1.40
    تين
    1.37
    POSITIVE LOGITS
    ला
    1.38
     tujuan
    1.05
     jaunâtre
    1.02
    മ
    1.00
     pubblic
    1.00
     imponer
    0.98
     bilangan
    0.96
    مر
    0.95
     it
    0.95
     université
    0.95
    Activations Density 0.003%

    No Known Activations