© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213857
    Prev
    Next
    INDEX
    Explanations

    subscriber record

    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
    ر
    1.34
    ר
    1.26
    不喜欢
    1.06
    د
    1.05
    ้น
    1.02
     can
    0.98
     vise
    0.97
    ன்
    0.90
    नोट
    0.90
    י
    0.90
    POSITIVE LOGITS
    is
    1.50
    కు
    1.41
    ти
    1.30
    де
    1.21
    지
    1.21
    ку
    1.19
    п
    1.17
    ла
    1.11
    تي
    1.11
    are
    1.10
    Activations Density 0.001%

    No Known Activations