© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41163
    Prev
    Next
    INDEX
    Explanations

    Polish and other Slavic language suffixes

    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_3_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
    '
    0.80
    ive
    0.79
    fortunately
    0.70
     muda
    0.69
    ят
    0.67
    াস
    0.67
    cient
    0.66
    ä
    0.66
    ка
    0.65
    ’
    0.65
    POSITIVE LOGITS
    ן
    0.86
    મ
    0.86
    트
    0.83
    ي
    0.83
    ur
    0.79
    ع
    0.79
    ط
    0.77
    ال
    0.75
    มัน
    0.74
    졌
    0.74
    Activations Density 0.000%

    No Known Activations