© 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. 214610
    Prev
    Next
    INDEX
    Explanations

    5 document

    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
     on
    1.25
    s
    1.13
    त
    1.05
    ের
    0.94
     {
    0.91
    ন
    0.86
     conglomerate
    0.85
    ли
    0.84
    ﺄ
    0.83
     переста
    0.80
    POSITIVE LOGITS
     it
    1.20
    it
    1.16
    hr
    0.98
    ج
    0.97
    ف
    0.89
    它
    0.89
    ков
    0.88
    zott
    0.87
     Plans
    0.86
    in
    0.86
    Activations Density 0.009%

    No Known Activations