© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199479
    Prev
    Next
    INDEX
    Explanations

    used for

    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_15_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
     Hö
    0.60
    ?“
    0.57
     Antônio
    0.56
    œ
    0.55
     Presidente
    0.55
    ಎಂ
    0.55
     Gün
    0.55
    捙
    0.55
    üste
    0.54
    Hö
    0.54
    POSITIVE LOGITS
    ست
    0.62
    モンド
    0.57
     родо
    0.57
     lineage
    0.55
    ﺸ
    0.55
    τα
    0.54
     desses
    0.54
     receptacle
    0.54
     thereof
    0.54
    xE
    0.53
    Activations Density 0.000%

    No Known Activations