© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45281
    Prev
    Next
    INDEX
    Explanations

    storytelling with data visualization

    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_22_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
     Jacksonville
    0.42
     CFM
    0.40
    ਼
    0.39
     ہاتھوں
    0.39
     brachial
    0.39
     ماسکو
    0.38
     embolism
    0.38
    荚
    0.37
     Raquel
    0.37
    બર
    0.37
    POSITIVE LOGITS
     domést
    0.40
     ምስ
    0.40
    α
    0.40
    asch
    0.39
    ligt
    0.39
    ləşdir
    0.39
    ioso
    0.39
     lebih
    0.39
     более
    0.38
    bach
    0.38
    Activations Density 0.008%

    No Known Activations