© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45792
    Prev
    Next
    INDEX
    Explanations

    society

    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_13_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
    0.36
     tror
    0.34
    ç
    0.32
     b
    0.32
    !)
    0.32
     n
    0.31
     t
    0.31
    ))
    0.31
     (
    0.30
     FORE
    0.30
    POSITIVE LOGITS
    hig
    0.38
    सामान्यीकृत
    0.37
     quirúrg
    0.36
    uolo
    0.35
    alten
    0.34
    ᄈ
    0.34
    agang
    0.34
    يارات
    0.33
    ᄑ
    0.33
    митри
    0.32
    Activations Density 0.004%

    No Known Activations