© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59355
    Prev
    Next
    INDEX
    Explanations

    JSON data format

    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_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
     usc
    0.61
     daje
    0.59
     ٹرسٹ
    0.59
    U
    0.59
     segue
    0.57
    IR
    0.55
     NVIDIA
    0.54
    NCE
    0.53
     cuant
    0.52
     diaz
    0.51
    POSITIVE LOGITS
    s
    0.87
    ts
    0.71
    ks
    0.63
    rl
    0.63
    ll
    0.59
    ke
    0.58
    ls
    0.57
    ft
    0.57
    rs
    0.55
    le
    0.54
    Activations Density 0.011%

    No Known Activations