© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90649
    Prev
    Next
    INDEX
    Explanations

    Kenzo / Kenji

    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_3_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
    Ⲗ
    0.62
     dehydrogen
    0.58
     (
    0.55
    omorphic
    0.53
    n
    0.52
     सीधा
    0.51
     sighted
    0.51
    ỡng
    0.51
     იყო
    0.50
     transcriptional
    0.50
    POSITIVE LOGITS
    UT
    0.91
    س
    0.89
    CL
    0.88
    RO
    0.87
    OS
    0.86
    CODE
    0.83
    f
    0.81
    ش
    0.80
    OT
    0.79
    د
    0.79
    Activations Density 0.000%

    No Known Activations