© 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. 36594
    Prev
    Next
    INDEX
    Explanations

    cv2.destroyAllWindows()

    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
     Teacher
    0.64
     y
    0.63
    <strong>
    0.62
     teacher
    0.62
    '
    0.61
    ’
    0.61
     তোমরা
    0.57
    teacher
    0.55
    í
    0.55
     você
    0.54
    POSITIVE LOGITS
    )。
    0.63
    க்கப்பட்டது
    0.59
    ICAGO
    0.57
    Empleado
    0.56
    ἲ
    0.54
     Pentland
    0.54
    玹
    0.52
     פון
    0.52
     Ensures
    0.52
    မ့်
    0.52
    Activations Density 0.000%

    No Known Activations