© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147146
    Prev
    Next
    INDEX
    Explanations

    smoke

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    тых
    0.40
    水
    0.37
    tım
    0.37
     water
    0.36
    েশনের
    0.35
    слов
    0.34
    춧
    0.34
    水量
    0.34
    സമയം
    0.34
    estion
    0.33
    POSITIVE LOGITS
     bill
    1.55
    bill
    1.41
    Bill
    1.38
     Bill
    1.30
    bills
    1.26
     bills
    1.19
     BILL
    1.16
    BILL
    1.16
    Bills
    1.14
     बिल
    1.11
    Activations Density 0.002%

    No Known Activations