© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5103
    Prev
    Next
    INDEX
    Explanations

    long answers because

    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_40_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
    Giovanni
    0.39
    Sponsored
    0.38
    Holy
    0.37
     Чем
    0.35
    创作
    0.35
     سنوات
    0.35
    搁
    0.35
    フロ
    0.34
     وعند
    0.34
     точек
    0.34
    POSITIVE LOGITS
     justice
    2.30
     Justice
    2.02
    Justice
    2.00
    justice
    1.97
     JUSTICE
    1.86
     justicia
    1.80
     justiça
    1.65
     न्याय
    1.55
     जस्टिस
    1.48
     Justiça
    1.40
    Activations Density 0.063%

    No Known Activations