© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170600
    Prev
    Next
    INDEX
    Explanations

    gotta do something

    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
     Existing
    0.30
    Existing
    0.30
    چار
    0.29
     spp
    0.28
    榖
    0.28
    
    0.27
     En
    0.27
    จร
    0.27
    ך
    0.26
     u
    0.26
    POSITIVE LOGITS
     কাটা
    0.32
    க்கப்படுகிறது
    0.32
    ம்தா
    0.32
    ITTLE
    0.28
     khử
    0.28
     asegura
    0.28
    ᱯ
    0.28
    рами
    0.28
    andin
    0.27
     crushed
    0.27
    Activations Density 0.004%

    No Known Activations