© 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. 59441
    Prev
    Next
    INDEX
    Explanations

    bachelor's degree or course

    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
     is
    1.23
    ری
    1.16
     in
    1.14
     I
    1.09
    ig
    1.09
     as
    1.07
    ре
    1.02
    пи
    1.00
    s
    0.97
     verwacht
    0.96
    POSITIVE LOGITS
    くらい
    1.32
    া
    1.27
    it
    1.19
    ه
    1.19
    ו
    1.15
    ，“
    1.13
    Categorie
    1.05
    (
    1.04
    ث
    1.04
    i
    1.02
    Activations Density 0.001%

    No Known Activations