© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131174
    Prev
    Next
    INDEX
    Explanations

    decoding ciphered text

    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_1_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
    ’
    1.64
     (
    0.95
    br
    0.93
    up
    0.91
    op
    0.91
    ’),
    0.89
    fr
    0.88
    ách
    0.82
    OL
    0.80
     tycoon
    0.79
    POSITIVE LOGITS
    t
    1.95
    ت
    1.77
    т
    1.59
    ۔
    1.52
    y
    1.48
    ৭
    1.47
    は
    1.46
    ។
    1.35
    ي
    1.33
    ری
    1.31
    Activations Density 0.001%

    No Known Activations