© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200208
    Prev
    Next
    INDEX
    Explanations

    wide

    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
     बाबर
    0.44
    Dependencies
    0.41
    razia
    0.41
    ay
    0.40
    犍
    0.39
    iedo
    0.39
    uroy
    0.39
    Tra
    0.38
     Prem
    0.38
    INESS
    0.38
    POSITIVE LOGITS
    maketitle
    0.43
     น
    0.41
     ডিভিশ
    0.40
    顶
    0.39
    спо
    0.38
    ffected
    0.38
    cinas
    0.38
    の時間
    0.37
    ภ
    0.37
    ASX
    0.37
    Activations Density 0.003%

    No Known Activations