© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215557
    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_50_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
     elektro
    0.42
     आरती
    0.42
    queros
    0.41
    ništva
    0.41
    J
    0.40
     Arth
    0.40
    Cotton
    0.39
     Jann
    0.39
    ϳ
    0.39
    Jean
    0.39
    POSITIVE LOGITS
     Bill
    0.47
     BILL
    0.44
     Expenses
    0.44
    Bill
    0.43
    Expenses
    0.42
     Bills
    0.40
    필
    0.40
     bill
    0.40
    滞
    0.40
     pul
    0.39
    Activations Density 0.000%

    No Known Activations