© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149678
    Prev
    Next
    INDEX
    Explanations

    World Wide Web

    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_18_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
    การ
    0.47
    re
    0.45
     n
    0.43
    the
    0.43
     New
    0.41
     wszystkie
    0.41
     모든
    0.38
     aby
    0.38
     과
    0.38
     Sadly
    0.38
    POSITIVE LOGITS
    нений
    0.40
    ৌজের
    0.40
    нер
    0.39
    нак
    0.37
     integrado
    0.37
    тт
    0.36
    нях
    0.36
    集成
    0.35
     电
    0.35
     missile
    0.35
    Activations Density 0.000%

    No Known Activations