© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85772
    Prev
    Next
    INDEX
    Explanations

    Notepad++

    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_3_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
    ’
    0.59
     ذكر
    0.58
     spielte
    0.54
     verkrij
    0.52
    InstanceOf
    0.51
     इंतजाम
    0.50
    人
    0.49
    UCK
    0.49
     hebt
    0.49
    人了
    0.48
    POSITIVE LOGITS
    3
    0.79
    6
    0.79
    qx
    0.67
    ましい
    0.66
    9
    0.60
     perturbations
    0.59
    를
    0.59
    4
    0.59
     on
    0.58
     निरी
    0.58
    Activations Density 0.012%

    No Known Activations