© 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. 40955
    Prev
    Next
    INDEX
    Explanations

    room number

    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
    साठी
    0.27
    면에
    0.26
    6
    0.26
    なら
    0.25
    ের
    0.25
    から
    0.24
    YPE
    0.24
    キロ
    0.23
    ６
    0.23
    っかけ
    0.23
    POSITIVE LOGITS
    ot
    0.38
     contamos
    0.30
     trabajador
    0.29
    resión
    0.27
    od
    0.26
    om
    0.26
    iería
    0.25
    itación
    0.25
     localizado
    0.24
    ographical
    0.24
    Activations Density 0.002%

    No Known Activations