© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20721
    Prev
    Next
    INDEX
    Explanations

    colleague

    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_56_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
     partner
    0.39
     companion
    0.37
     Partner
    0.35
     accompaniment
    0.34
    ရှင်း
    0.34
    同
    0.33
     diikuti
    0.33
    ῎
    0.32
    盗
    0.31
     partenaire
    0.31
    POSITIVE LOGITS
     colle
    2.86
     kole
    2.67
     Colle
    2.67
     коле
    2.64
     COLLE
    2.61
     cole
    2.59
     колле
    2.45
     coll
    2.33
     colleg
    2.31
    Cole
    2.30
    Activations Density 0.030%

    No Known Activations