© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207706
    Prev
    Next
    INDEX
    Explanations

    precision, speed, second

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    2
    0.17
     altro
    0.16
    iolet
    0.16
    ados
    0.15
     endorsements
    0.15
     allowable
    0.15
     executions
    0.15
     partitions
    0.15
    t
    0.15
    ruppe
    0.15
    POSITIVE LOGITS
    ور
    0.17
    T
    0.16
     Nasıl
    0.15
    وا
    0.15
    റ്റ്
    0.15
    يت
    0.15
    أن
    0.15
    ع
    0.15
    ра
    0.15
    ٣
    0.15
    Activations Density 0.001%

    No Known Activations