© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56981
    Prev
    Next
    INDEX
    Explanations

    observational study and humor

    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_11_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
    '
    0.28
     Servlet
    0.28
     תי
    0.25
    x
    0.24
     เง
    0.23
     మి
    0.23
     objekt
    0.23
    voll
    0.22
     Prix
    0.22
     meerdere
    0.22
    POSITIVE LOGITS
    ဦ
    0.27
    ᱘
    0.25
    кість
    0.24
    す
    0.24
    棉
    0.23
    dui
    0.23
    )，
    0.23
    しい
    0.23
    し
    0.22
    ７
    0.22
    Activations Density 0.018%

    No Known Activations