© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    factual information or proof

    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
    юнча
    0.38
    বিস্তারিত
    0.38
    閎
    0.36
    தாவது
    0.35
    ынша
    0.33
    番
    0.33
    祟
    0.32
    ╥
    0.32
     لاز
    0.31
     অধ্যক্ষ
    0.31
    POSITIVE LOGITS
     fact
    2.48
    Fact
    2.20
     Fact
    2.17
    fact
    2.08
     facts
    2.05
     fakt
    2.03
     фак
    2.02
     факт
    2.00
    FACT
    1.99
    事実
    1.97
    Activations Density 0.109%

    No Known Activations