© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5484
    Prev
    Next
    INDEX
    Explanations

    say "="

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    uros
    0.27
    AllRef
    0.26
    mygray
    0.23
     multit
    0.23
    పు
    0.22
     persen
    0.22
     Всего
    0.22
    麸
    0.21
     дове
    0.21
     Dams
    0.21
    POSITIVE LOGITS
     Hick
    0.25
     Hig
    0.25
     Higgins
    0.25
     tích
    0.24
    ifferentiate
    0.24
     Hiram
    0.23
     ethically
    0.22
     Hendrick
    0.22
    Hig
    0.22
     Moy
    0.22
    Activations Density 0.002%

    No Known Activations