© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228442
    Prev
    Next
    INDEX
    Explanations

    cipher shift

    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_6_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
     was
    0.65
    ру
    0.62
    0.61
    า
    0.57
     র
    0.56
    お金
    0.54
     is
    0.54
    お子
    0.53
    ير
    0.52
    おそらく
    0.52
    POSITIVE LOGITS
    as
    0.84
    er
    0.69
    지
    0.66
    o
    0.64
    ar
    0.61
    eer
    0.59
    eight
    0.58
    full
    0.57
    feng
    0.55
    H
    0.55
    Activations Density 0.000%

    No Known Activations