© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108331
    Prev
    Next
    INDEX
    Explanations

    Jotunheim or Midgard

    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_2_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
    ن
    1.52
    न
    1.36
    การ
    1.33
    3
    1.32
    4
    1.32
    förm
    1.29
    2
    1.23
    1
    1.20
    स
    1.19
    ก็
    1.18
    POSITIVE LOGITS
     سكان
    1.17
     كات
    1.09
     solide
    1.09
    ﺕ
    1.08
     تصميم
    1.05
     Прави
    1.03
     كري
    1.03
     conceitos
    1.00
     campione
    1.00
    ﺖ
    1.00
    Activations Density 0.000%

    No Known Activations