© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79533
    Prev
    Next
    INDEX
    Explanations

    symmetric encryption and information

    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_0_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
    υ
    1.63
    MA
    1.44
    OS
    1.38
    IP
    1.37
    ES
    1.31
    ID
    1.30
    OC
    1.30
    AT
    1.28
    EN
    1.28
    AG
    1.28
    POSITIVE LOGITS
    '
    2.20
    ن
    1.88
    de
    1.83
    n
    1.78
    li
    1.53
    та
    1.52
    ll
    1.51
    th
    1.50
    nn
    1.48
    tm
    1.41
    Activations Density 0.000%

    No Known Activations