© 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. 196335
    Prev
    Next
    INDEX
    Explanations

    derived marker

    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
    窪
    0.43
    $/../../
    0.42
     непо
    0.40
    ენი
    0.40
    urais
    0.39
     нев
    0.38
     у
    0.37
    出て
    0.37
    ウ
    0.36
    empo
    0.35
    POSITIVE LOGITS
     zá
    0.40
     Mick
    0.38
    ton
    0.37
    Zoom
    0.37
     zas
    0.37
     सीता
    0.36
     Ges
    0.35
    derived
    0.35
    पुरुष
    0.35
     Marker
    0.35
    Activations Density 0.003%

    No Known Activations