© 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. 39534
    Prev
    Next
    INDEX
    Explanations

    we want to find

    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
    （
    0.80
     L
    0.77
    H
    0.76
    k
    0.73
    0.72
    A
    0.71
    P
    0.70
    D
    0.70
    L
    0.67
    Is
    0.66
    POSITIVE LOGITS
     mesmos
    0.78
     nossas
    0.75
     ourselves
    0.73
     ہماری
    0.73
    矸
    0.73
     venons
    0.72
    ajemy
    0.71
     हाम्रो
    0.71
     tuvimos
    0.70
    仨
    0.69
    Activations Density 0.020%

    No Known Activations