© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261042
    Prev
    Next
    INDEX
    Explanations

    some of

    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_22_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
     :\
    0.32
     redemption
    0.31
     sow
    0.31
    )-\
    0.28
    emon
    0.28
    ermott
    0.27
     calligraphy
    0.27
    জিও
    0.27
     ثلاثة
    0.27
     lemma
    0.27
    POSITIVE LOGITS
    ස්
    0.39
     yoki
    0.35
     championed
    0.33
    𐰣
    0.33
    ዉ
    0.32
     Kipp
    0.32
     الفي
    0.31
    或者
    0.31
    或者是
    0.31
    ΑΣ
    0.31
    Activations Density 0.006%

    No Known Activations