© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43224
    Prev
    Next
    INDEX
    Explanations

    encryption and decryption mechanisms

    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_22_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
    朼
    0.38
     encrypted
    0.38
     ஷ
    0.38
     www
    0.37
     pepper
    0.37
     teslim
    0.37
     বিশ্বের
    0.37
     encodes
    0.37
     encoded
    0.36
    ්‍ර
    0.36
    POSITIVE LOGITS
     unfavorable
    0.40
     Ples
    0.39
     contentment
    0.39
     mindre
    0.39
     Bahamas
    0.38
    만
    0.37
    ళ్ళు
    0.36
     DMT
    0.36
    ปลี่ยน
    0.35
     Ponce
    0.35
    Activations Density 0.004%

    No Known Activations