© 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. 211765
    Prev
    Next
    INDEX
    Explanations

    or/on

    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
    ق
    1.31
    ти
    1.25
    c
    1.16
    ن
    1.08
    ור
    1.05
    는데
    1.05
    ্স
    1.02
    st
    1.00
    د
    0.95
    ב
    0.94
    POSITIVE LOGITS
    다
    1.44
    t
    1.41
    től
    1.13
     utiliz
    1.11
     broadcaster
    1.09
    डी
    1.07
     piattaforma
    1.07
     divulg
    1.05
     lượng
    1.05
    ການ
    1.04
    Activations Density 0.000%

    No Known Activations