© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225106
    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
    ្នាំ
    0.48
    酮
    0.46
    <0x94>
    0.42
    ই
    0.41
    alone
    0.39
    释放
    0.38
    ստ
    0.38
    吸収
    0.38
    رو
    0.38
    絮
    0.38
    POSITIVE LOGITS
     Pam
    0.50
     permettant
    0.50
     souvenirs
    0.50
     מש
    0.48
     advertisements
    0.48
     chargés
    0.48
     reporters
    0.47
     Sauv
    0.47
     pamphlets
    0.47
     দশ
    0.47
    Activations Density 0.000%

    No Known Activations