© 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. 179076
    Prev
    Next
    INDEX
    Explanations

    institution or lab

    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
     Textile
    0.40
     Bateman
    0.38
    iphenyl
    0.37
    QSpacerItem
    0.36
     Doug
    0.36
    SSP
    0.36
    巨
    0.36
     ک
    0.35
     থাকলেও
    0.35
    ỏi
    0.35
    POSITIVE LOGITS
     INSTITUTE
    0.46
     Institute
    0.46
    Institute
    0.43
     इंस्टीट्यूट
    0.40
     उत्सव
    0.38
     desk
    0.37
     водо
    0.37
     nonlocal
    0.36
    regulating
    0.36
    撾
    0.36
    Activations Density 0.001%

    No Known Activations