© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59862
    Prev
    Next
    INDEX
    Explanations

    service disruption

    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
     in
    1.64
     is
    1.48
    ق
    1.43
    ح
    1.43
    ك
    1.38
    ط
    1.37
    人
    1.37
    dır
    1.33
    ف
    1.30
    ld
    1.27
    POSITIVE LOGITS
    یم
    1.20
    வர்கள்
    1.16
    u
    1.14
    ھا
    1.12
    ی
    1.12
     lumea
    1.09
    ０
    1.09
     ayaa
    1.06
    ación
    1.05
     vê
    1.05
    Activations Density 0.002%

    No Known Activations