© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206190
    Prev
    Next
    INDEX
    Explanations

    overalls

    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
     ملاحظ
    0.60
    ปล่อย
    0.54
     πίνα
    0.54
     ก
    0.53
     सामान
    0.53
    只是
    0.52
    ค
    0.52
     एह
    0.51
     ثابت
    0.50
    จ่าย
    0.50
    POSITIVE LOGITS
    на
    0.71
    na
    0.60
    canada
    0.59
    Allows
    0.58
    াস
    0.57
    ).[
    0.57
    )(
    0.57
    )[
    0.55
    ავ
    0.55
    AZ
    0.55
    Activations Density 0.000%

    No Known Activations