© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207925
    Prev
    Next
    INDEX
    Explanations

    test understanding

    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_19_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
    quiao
    0.54
     ScriptInterface
    0.50
    ◅
    0.49
     Когда
    0.47
    伌
    0.47
     fermé
    0.47
     когда
    0.45
     vuurp
    0.45
    偪
    0.44
    сант
    0.43
    POSITIVE LOGITS
    approximately
    0.46
     approximately
    0.41
    met
    0.41
     seven
    0.40
    selective
    0.40
     selective
    0.40
    QC
    0.40
     seme
    0.39
    held
    0.39
     thickness
    0.38
    Activations Density 0.004%

    No Known Activations