© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174352
    Prev
    Next
    INDEX
    Explanations

    earth

    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_20_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
     chase
    0.28
    CTURE
    0.28
    ствовал
    0.28
     restructure
    0.28
     restructuring
    0.27
     النار
    0.26
    ៊
    0.25
    üdis
    0.25
    ঞ্চল্য
    0.24
     dominant
    0.24
    POSITIVE LOGITS
    Families
    0.26
     \
    0.25
     families
    0.25
    families
    0.25
     परिवारों
    0.25
     famílias
    0.25
    ax
    0.24
     ระ
    0.24
    Reference
    0.23
    ..</
    0.23
    Activations Density 0.003%

    No Known Activations