© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161274
    Prev
    Next
    INDEX
    Explanations

    other than in

    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_2_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
    y
    1.99
    k
    1.48
    res
    1.30
    brough
    1.26
    تان
    1.18
    SO
    1.16
    ,
    1.15
    CF
    1.14
    yout
    1.13
    تون
    1.12
    POSITIVE LOGITS
     in
    2.13
    在
    1.69
    ى
    1.42
    يد
    1.32
    у
    1.26
    ة
    1.26
     في
    1.24
    도
    1.17
    লা
    1.16
    ใน
    1.16
    Activations Density 0.002%

    No Known Activations