© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222993
    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_10_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
    ສຸດ
    0.54
    旳
    0.48
    粓
    0.47
    йы
    0.44
    ঠা
    0.44
     viciss
    0.44
    ător
    0.44
     duplicating
    0.42
    联邦
    0.41
     bevel
    0.41
    POSITIVE LOGITS
    otype
    0.46
     কর্মকাণ্ড
    0.44
     बंध
    0.43
     शख्स
    0.42
    OLO
    0.42
    )}{\
    0.42
    unu
    0.42
    ectomy
    0.42
    ulnerability
    0.41
     طرح
    0.41
    Activations Density 0.000%

    No Known Activations