© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207950
    Prev
    Next
    INDEX
    Explanations

    arithmetic mean

    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_19_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
    /),
    0.47
     dedicato
    0.46
     spannend
    0.46
     философии
    0.46
    braith
    0.46
    cherche
    0.45
     beinh
    0.44
     vrai
    0.44
    ೃದ್ಧ
    0.44
     frank
    0.43
    POSITIVE LOGITS
    陸
    0.47
    6
    0.46
    を
    0.44
     nail
    0.44
     sip
    0.44
       
    0.43
    土地
    0.43
     density
    0.43
     damper
    0.43
    限制
    0.42
    Activations Density 0.001%

    No Known Activations