© 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. 61396
    Prev
    Next
    INDEX
    Explanations

    lean towards|into|heavily

    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
     -
    0.68
     Euras
    0.61
     Erfahr
    0.59
     ^
    0.57
     Evolution
    0.57
    Fotos
    0.57
     Overview
    0.56
     Approximate
    0.56
     Oreo
    0.55
     Architecture
    0.54
    POSITIVE LOGITS
    出
    0.58
     বাইরে
    0.55
     calles
    0.54
     gamanam
    0.53
     معاملہ
    0.52
    ကြ
    0.51
     viajeros
    0.51
    은
    0.51
    ти
    0.50
     emergencies
    0.50
    Activations Density 0.008%

    No Known Activations