© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198757
    Prev
    Next
    INDEX
    Explanations

    impression

    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_46_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
     microseconds
    0.37
    Rustic
    0.37
    ဖြင့်
    0.37
    があり
    0.36
    Lig
    0.36
     pesso
    0.35
    zysz
    0.35
    裴
    0.35
    mocks
    0.35
     বয়সী
    0.34
    POSITIVE LOGITS
    transcript
    0.40
    巢
    0.38
    ét
    0.37
    ianz
    0.37
    iest
    0.37
     taraf
    0.37
    éma
    0.37
    榜
    0.36
    摺
    0.36
     Nova
    0.36
    Activations Density 0.001%

    No Known Activations