© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42571
    Prev
    Next
    INDEX
    Explanations

    ensure or make sure

    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_13_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
    LLA
    0.67
    ल
    0.66
    resión
    0.64
    רי
    0.61
    ವುದು
    0.61
    ޝ
    0.61
    стви
    0.61
    ל
    0.61
    ன்
    0.60
    دی
    0.59
    POSITIVE LOGITS
    time
    0.52
    kovskij
    0.52
    kem
    0.50
    hog
    0.49
     honor
    0.49
     honour
    0.48
    अय
    0.48
     وح
    0.47
    kových
    0.46
    sustaining
    0.46
    Activations Density 0.005%

    No Known Activations