© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68520
    Prev
    Next
    INDEX
    Explanations

    Elara

    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_51_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
     (£
    0.41
    酋
    0.40
     Кан
    0.38
     Clim
    0.38
    ℂ
    0.38
     Klima
    0.38
    ęcie
    0.38
    cookie
    0.37
     sente
    0.37
     klima
    0.36
    POSITIVE LOGITS
    დას
    0.42
     infringed
    0.39
    UpdatedAt
    0.38
    Survived
    0.38
    Erin
    0.37
    泰
    0.36
     speeding
    0.36
     battered
    0.36
    कूल
    0.35
    FT
    0.35
    Activations Density 0.002%

    No Known Activations