© 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. 107336
    Prev
    Next
    INDEX
    Explanations

    tagalog

    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
    ק
    1.69
     are
    1.56
    д
    1.23
    in
    1.17
    ক
    1.17
     as
    1.16
    p
    1.13
    ፣
    1.13
    क
    1.13
    f
    1.09
    POSITIVE LOGITS
    .
    1.03
    ভাবে
    0.93
    സ്ത്ര
    0.91
    কে
    0.89
     قادر
    0.81
    이지만
    0.78
     portent
    0.73
     degli
    0.72
     discuter
    0.72
     watchdog
    0.71
    Activations Density 0.000%

    No Known Activations