© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105248
    Prev
    Next
    INDEX
    Explanations

    Filipino and Tagalog words

    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_1_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
    ing
    1.62
    า
    1.49
    ة
    1.45
    ul
    1.36
    ก
    1.36
     are
    1.34
    il
    1.27
    n
    1.25
     can
    1.19
    ა
    1.16
    POSITIVE LOGITS
    પણ
    1.13
    1
    1.09
    CL
    1.06
    ’
    1.06
    0
    1.05
    manship
    0.96
    LAW
    0.95
    Platforms
    0.94
    And
    0.93
    CD
    0.93
    Activations Density 0.000%

    No Known Activations