© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78384
    Prev
    Next
    INDEX
    Explanations

    foreign language characters in parentheses

    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_29_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
     hereinafter
    0.40
    ော်
    0.38
    +}(
    0.36
    Przeczytaj
    0.36
     Hallo
    0.36
     вере
    0.36
     ordination
    0.34
     September
    0.34
     Ord
    0.34
    隗
    0.34
    POSITIVE LOGITS
     boundaries
    0.40
    以及
    0.40
    ྥ
    0.40
     borders
    0.39
    擁有
    0.38
     चलाते
    0.38
    зион
    0.38
    dominant
    0.38
     dominate
    0.38
    timezone
    0.38
    Activations Density 0.014%

    No Known Activations