© 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. 179234
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    
    0.36
    ˂
    0.36
    Clientes
    0.35
    ᆢ
    0.35
    IndexOf
    0.35
    Toolkit
    0.34
     mempers
    0.33
    ʺ
    0.33
    toolkit
    0.32
    (<
    0.32
    POSITIVE LOGITS
    وري
    0.37
     lames
    0.35
     экзем
    0.35
    zg
    0.34
    yra
    0.34
     Sudan
    0.34
     shame
    0.33
     Triple
    0.33
    żs
    0.33
     przec
    0.33
    Activations Density 0.000%

    No Known Activations