© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164825
    Prev
    Next
    INDEX
    Explanations

    widescreen aspect ratio (16:9)

    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_13_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
    庴
    0.19
    r
    0.18
    garden
    0.17
     Wood
    0.17
     Court
    0.17
    embed
    0.17
     Oppen
    0.16
    diss
    0.16
     Exotic
    0.16
    b
    0.16
    POSITIVE LOGITS
    ovariant
    0.17
    ስቃሴ
    0.17
     strumenti
    0.17
     clotting
    0.17
     sera
    0.16
     sécurité
    0.16
    协同
    0.16
     nadi
    0.16
    战斗
    0.16
    蹑
    0.16
    Activations Density 0.008%

    No Known Activations