© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130103
    Prev
    Next
    INDEX
    Explanations

    ticks all the boxes

    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_6_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
    EN
    0.81
     publicados
    0.75
     செய்யப்படும்
    0.73
    ﻼ
    0.73
    =>{
    0.71
     obstáculos
    0.70
    rī
    0.70
     produz
    0.69
     către
    0.68
    ActionBar
    0.68
    POSITIVE LOGITS
    with
    1.01
    ви
    0.93
     be
    0.93
    w
    0.93
    ה
    0.92
    е
    0.92
    ция
    0.89
    ur
    0.86
    ک
    0.86
    isering
    0.85
    Activations Density 0.000%

    No Known Activations