© 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. 112062
    Prev
    Next
    INDEX
    Explanations

    Greek words and 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_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
    ని
    0.95
    ación
    0.89
    ல்
    0.82
    ства
    0.79
    ,
    0.79
    ución
    0.76
    ból
    0.76
    ро
    0.75
    IN
    0.74
    ем
    0.73
    POSITIVE LOGITS
     in
    1.17
    一
    1.00
    a
    0.95
    v
    0.93
    ד
    0.89
    在
    0.87
     في
    0.86
     on
    0.80
     an
    0.80
    信息化
    0.79
    Activations Density 0.000%

    No Known Activations