© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90511
    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_11_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
     season
    0.45
    的多
    0.43
     শ
    0.43
     आहे
    0.43
    ib
    0.43
    terne
    0.42
     Warriors
    0.42
    jší
    0.41
     může
    0.41
    Z
    0.41
    POSITIVE LOGITS
    s
    0.64
     accusation
    0.53
    ים
    0.49
    <unused2144>
    0.48
    साहेब
    0.47
     ಅರ್
    0.46
     اگلے
    0.46
     lengua
    0.46
    കേന്ദ്രം
    0.46
     acusado
    0.45
    Activations Density 0.000%

    No Known Activations