© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215628
    Prev
    Next
    INDEX
    Explanations

    Tik

    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_50_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
    OMX
    0.40
     facie
    0.39
    銘
    0.39
    ᒫ
    0.39
    legten
    0.38
     rougeâtres
    0.38
    滘
    0.38
    ALING
    0.36
    ложи
    0.36
     Ammonia
    0.36
    POSITIVE LOGITS
    زاز
    0.44
     Yo
    0.43
    欺
    0.40
    yo
    0.40
    zechoslovak
    0.39
     sui
    0.39
    BarButtonItem
    0.39
    ヨ
    0.39
    ulas
    0.38
    বার্তা
    0.38
    Activations Density 0.000%

    No Known Activations