© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54559
    Prev
    Next
    INDEX
    Explanations

    staff

    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_55_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
     convient
    0.39
     formContext
    0.37
    敛
    0.36
     revolution
    0.35
     그리고
    0.34
     powdered
    0.33
     cory
    0.32
    heus
    0.32
     सरकारी
    0.32
    ङ
    0.32
    POSITIVE LOGITS
     members
    1.26
    members
    1.19
     Members
    1.13
    Members
    1.10
    メンバー
    1.02
     membres
    0.98
    成员
    0.95
     miembros
    0.95
     membros
    0.93
     सदस्यों
    0.91
    Activations Density 0.005%

    No Known Activations