© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60634
    Prev
    Next
    INDEX
    Explanations

    significance

    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
    5
    0.50
    NR
    0.49
    CAR
    0.48
    _
    0.47
    acchi
    0.46
    ANE
    0.46
    EY
    0.46
    ."
    0.45
    โป
    0.44
    一些
    0.44
    POSITIVE LOGITS
     alleviated
    0.51
    ᱙
    0.49
     haue
    0.49
    ખ્ય
    0.46
     disagreed
    0.46
    Bigr
    0.46
     prevented
    0.45
    istungen
    0.45
     ionized
    0.45
    लाइजेशन
    0.45
    Activations Density 0.000%

    No Known Activations