© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227951
    Prev
    Next
    INDEX
    Explanations

    word endings in multiple languages

    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_6_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
    is
    1.40
    т
    1.25
    ม
    1.22
    '
    1.20
    ی
    1.20
    は
    1.14
    ির
    1.12
    ین
    1.11
    s
    1.10
     is
    1.09
    POSITIVE LOGITS
    rón
    0.87
    ión
    0.81
    rás
    0.81
    كة
    0.78
    ékony
    0.77
     ပ
    0.76
    izarre
    0.74
    lake
    0.74
    booking
    0.73
    ၅
    0.72
    Activations Density 0.000%

    No Known Activations