© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97863
    Prev
    Next
    INDEX
    Explanations

    Billboard music charts

    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_14_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
    埇
    0.15
    猢
    0.13
     nasıl
    0.13
    🥙
    0.12
     неё
    0.12
    uscular
    0.12
     каким
    0.12
    🤛
    0.12
     Lordships
    0.12
     laterales
    0.12
    POSITIVE LOGITS
    class
    0.12
    提
    0.12
    ichtung
    0.12
    itare
    0.11
     fetching
    0.11
     looked
    0.11
    stories
    0.11
    ാം
    0.11
    fetched
    0.11
    schen
    0.11
    Activations Density 0.004%

    No Known Activations