© 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. 108461
    Prev
    Next
    INDEX
    Explanations

    fuel-efficient cars, vehicles, and aircraft

    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
    在
    1.27
    ión
    1.14
    ，
    1.08
    着
    1.06
    nés
    1.05
     bezoek
    1.02
    ší
    1.02
    ção
    1.00
    ous
    0.99
    ized
    0.97
    POSITIVE LOGITS
    ת
    2.06
    ן
    1.70
    ים
    1.52
    ти
    1.45
    ut
    1.43
    ം
    1.43
    ו
    1.41
    ע
    1.41
    та
    1.41
    תה
    1.38
    Activations Density 0.004%

    No Known Activations