© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
     इसको
    0.53
    ન્દ્ર
    0.52
    튀
    0.49
    ມັນ
    0.49
    arán
    0.49
     it
    0.48
     invariably
    0.47
    มัน
    0.47
    Ự
    0.47
     هيبقى
    0.47
    POSITIVE LOGITS
    desde
    0.53
     lager
    0.52
     commercial
    0.50
    than
    0.47
     trent
    0.44
    during
    0.44
    COS
    0.43
     celestial
    0.43
    專業
    0.43
    me
    0.42
    Activations Density 0.000%

    No Known Activations