© 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. 36418
    Prev
    Next
    INDEX
    Explanations

    start a

    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
    Runtime
    0.62
    prim
    0.59
    1
    0.56
    burg
    0.56
    Template
    0.56
    Debug
    0.54
    特
    0.54
    construct
    0.53
    Printer
    0.52
    Default
    0.52
    POSITIVE LOGITS
     memperhatikan
    0.71
    ivasena
    0.69
    ⺊
    0.66
    avkh
    0.66
     Ore
    0.65
    »),
    0.65
    abbanti
    0.64
    aparikkh
    0.64
    okkh
    0.64
     According
    0.63
    Activations Density 0.004%

    No Known Activations