© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29288
    Prev
    Next
    INDEX
    Explanations

    will/should followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     применять
    0.38
    দেখে
    0.38
     황
    0.37
     *)&
    0.37
    "$
    0.37
     पाच
    0.36
     diterapkan
    0.36
     colloidal
    0.35
     تشوف
    0.35
     /$
    0.35
    POSITIVE LOGITS
     format
    0.67
    格式
    0.59
     Format
    0.58
     formate
    0.57
    format
    0.57
     formats
    0.53
     FORMAT
    0.51
     formato
    0.51
     формат
    0.51
    Format
    0.50
    Activations Density 0.036%

    No Known Activations