© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137696
    Prev
    Next
    INDEX
    Explanations

    statistical deviation and mode

    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_12_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
    ni
    0.61
     সেখানে
    0.50
    si
    0.48
    su
    0.48
    mo
    0.47
    cami
    0.47
    γρα
    0.47
    ।
    0.47
    Suppress
    0.47
    dır
    0.46
    POSITIVE LOGITS
    ้อน
    0.49
     lẫn
    0.49
    ย
    0.47
     б
    0.45
     سپورت
    0.44
     Laplacian
    0.43
     deviation
    0.42
     crooked
    0.42
     بیش
    0.42
    นำ
    0.41
    Activations Density 0.001%

    No Known Activations