© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215619
    Prev
    Next
    INDEX
    Explanations

    code comments

    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_5_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
    is
    1.27
    ᱗
    1.27
    ៥
    1.25
    y
    1.20
    _
    1.17
    {
    1.17
    𝐰
    1.16
    bv
    1.13
     ي
    1.11
     depreci
    1.10
    POSITIVE LOGITS
    ر
    1.70
    คะ
    1.14
    ความ
    1.06
    ת
    1.05
    ัง
    1.04
    ق
    1.02
    ש
    1.02
    สิ่ง
    0.99
    ทุก
    0.98
    لی
    0.95
    Activations Density 0.000%

    No Known Activations