© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197046
    Prev
    Next
    INDEX
    Explanations

    for and against

    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_46_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
    পথ
    0.40
     EE
    0.39
     Doors
    0.38
     Nachricht
    0.38
    罌
    0.38
     ku
    0.37
     Kaf
    0.37
    igenschaft
    0.37
     Rees
    0.37
     kres
    0.36
    POSITIVE LOGITS
    덕
    0.37
    ที่เป็น
    0.36
    ionic
    0.35
    beige
    0.35
    発売
    0.34
     הראשון
    0.34
    urid
    0.34
     রহমান
    0.34
    First
    0.33
    Bearer
    0.33
    Activations Density 0.007%

    No Known Activations