© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210352
    Prev
    Next
    INDEX
    Explanations

    OS, VM, HTTP, system, object

    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_5_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
    ä
    1.24
    _
    1.14
    ad
    1.13
    (
    1.05
    gence
    0.97
    ية
    0.97
    á
    0.96
     and
    0.95
    c
    0.94
     or
    0.91
    POSITIVE LOGITS
    י
    1.30
    らの
    0.97
     Đế
    0.94
    بي
    0.93
    ي
    0.93
    いです
    0.89
    らは
    0.88
     تھے
    0.88
     filthy
    0.88
     CFRP
    0.87
    Activations Density 0.000%

    No Known Activations