© 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. 123131
    Prev
    Next
    INDEX
    Explanations

    leather, alter, ' Olsen, ' stole, '

    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
    ক
    0.84
    า
    0.80
    ।
    0.77
     touchdowns
    0.72
     can
    0.71
    ม
    0.70
    ".
    0.69
    았다
    0.68
    .")
    0.65
    ا۔
    0.65
    POSITIVE LOGITS
    ell
    0.60
    り
    0.54
    abling
    0.54
    ě
    0.54
     الثلاث
    0.53
     ప్రధాన
    0.53
    ول
    0.52
    polymer
    0.52
    ें
    0.52
    dob
    0.51
    Activations Density 0.006%

    No Known Activations