© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261469
    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_22_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
    acking
    0.46
     stopped
    0.43
     pend
    0.42
    ג
    0.41
     ETL
    0.41
     ה
    0.41
     స
    0.41
     quer
    0.41
    ეთის
    0.41
    zs
    0.40
    POSITIVE LOGITS
     Vicar
    0.49
     vicar
    0.48
    龴
    0.46
    arid
    0.45
    㪇
    0.45
     víct
    0.43
     fortiter
    0.43
    忘れ
    0.42
     मेजब
    0.42
    侸
    0.42
    Activations Density 0.000%

    No Known Activations