© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160211
    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_2_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
     CERN
    0.96
     IU
    0.96
    lara
    0.90
     legate
    0.89
    0
    0.89
    TA
    0.88
     IUCN
    0.88
    ARE
    0.87
    ারন
    0.87
    োনা
    0.86
    POSITIVE LOGITS
    да
    1.09
    ط
    1.05
    人材
    0.96
    人
    0.96
    ان
    0.95
    掝
    0.94
    <0xAC>
    0.92
    些
    0.90
    на
    0.88
    ли
    0.88
    Activations Density 0.000%

    No Known Activations