© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210711
    Prev
    Next
    INDEX
    Explanations

    Johan Cruyff

    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_5_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
    خ
    0.77
    ند
    0.73
    od
    0.72
    ,
    0.71
    ן
    0.66
     of
    0.65
    ست
    0.65
    ما
    0.65
    ast
    0.62
    هم
    0.62
    POSITIVE LOGITS
     slučaj
    0.71
    의
    0.70
    ﻜ
    0.70
    ﺒ
    0.69
     anál
    0.68
    の
    0.68
    ﻨ
    0.67
    ın
    0.66
    ﺌ
    0.65
     پیسې
    0.64
    Activations Density 0.000%

    No Known Activations