© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163907
    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_13_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
    сет
    0.64
     قيم
    0.59
    ים
    0.58
     സ്ഥി
    0.53
     стой
    0.52
    ের
    0.52
     ใส่
    0.51
    ;/
    0.50
     Marissa
    0.50
     thermost
    0.49
    POSITIVE LOGITS
    ha
    0.69
    arian
    0.55
    hor
    0.52
    They
    0.52
    ce
    0.50
    err
    0.50
    byshire
    0.49
    ரிக்கை
    0.47
    ari
    0.47
    Research
    0.47
    Activations Density 0.000%

    No Known Activations