© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37382
    Prev
    Next
    INDEX
    Explanations

    SRX Firewalls or Property

    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
     I
    0.82
    I
    0.82
     (
    0.78
    A
    0.67
    og
    0.63
    ва
    0.62
    inig
    0.61
    ர்த்து
    0.60
    ்ட்
    0.59
    었어요
    0.59
    POSITIVE LOGITS
    ne
    0.85
    t
    0.79
    ING
    0.76
     is
    0.74
    सी
    0.73
    IS
    0.71
    은
    0.70
    オート
    0.69
    מ
    0.69
    zelf
    0.68
    Activations Density 0.000%

    No Known Activations