© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177655
    Prev
    Next
    INDEX
    Explanations

    crafted

    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
    羈
    0.42
    含义
    0.38
    preneur
    0.37
    ematic
    0.36
     membre
    0.36
     magist
    0.35
    hetical
    0.35
     angelic
    0.35
     LSP
    0.35
    etable
    0.35
    POSITIVE LOGITS
     ষ
    0.38
    妥
    0.37
    pleo
    0.37
    illo
    0.36
    適
    0.36
    
    0.36
    Validation
    0.36
    适当
    0.35
    월
    0.35
    Ар
    0.34
    Activations Density 0.004%

    No Known Activations