© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25237
    Prev
    Next
    INDEX
    Explanations

    `is` `focused` or `is` `filled`

    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_10_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
    t
    0.32
    lose
    0.25
    ton
    0.24
    recyclerview
    0.23
    se
    0.23
    son
    0.22
    ki
    0.22
    lev
    0.22
    pan
    0.22
    me
    0.21
    POSITIVE LOGITS
     cinq
    0.26
    و
    0.25
     quatre
    0.25
     acab
    0.24
     fifth
    0.24
     قي
    0.23
    とっても
    0.23
    ৮
    0.23
     к
    0.23
     quatro
    0.23
    Activations Density 0.457%

    No Known Activations