© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83976
    Prev
    Next
    INDEX
    Explanations

    Polish and Italian interjections

    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_0_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
    ی
    2.16
    т
    1.95
    м
    1.94
     cambios
    1.78
    ラ
    1.66
    на
    1.66
    ก
    1.66
    त
    1.63
    ம்
    1.56
    ים
    1.55
    POSITIVE LOGITS
    itt
    1.66
     of
    1.44
    yn
    1.42
    ib
    1.38
    ige
    1.38
    ama
    1.36
    ess
    1.34
    iel
    1.31
    ite
    1.30
     for
    1.29
    Activations Density 0.000%

    No Known Activations