© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35650
    Prev
    Next
    INDEX
    Explanations

    headline

    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_11_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
    なくなる
    0.61
     hə
    0.55
     g
    0.53
     लॉग
    0.53
    ropical
    0.53
     mensagem
    0.52
    HttpMethod
    0.51
     servlet
    0.51
    )</
    0.50
     hamlet
    0.50
    POSITIVE LOGITS
    ennia
    0.55
    tti
    0.54
     Into
    0.52
     Neel
    0.52
    ad
    0.51
    atschapp
    0.51
     Simply
    0.50
    సి
    0.49
     UT
    0.49
     Aurora
    0.49
    Activations Density 0.000%

    No Known Activations