© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19084
    Prev
    Next
    INDEX
    Explanations

    let me know

    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_15_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
     എന്നാണ്
    0.29
     sekä
    0.28
    蒸汽
    0.28
     När
    0.27
     zwar
    0.27
    </b>
    0.26
     Mä
    0.26
    emen
    0.26
     від
    0.26
    ஸ்வர
    0.26
    POSITIVE LOGITS
     probabil
    0.25
    رداری
    0.25
     pebble
    0.24
     gurus
    0.24
     morphed
    0.24
     fundraiser
    0.23
     airport
    0.23
     कर्मी
    0.23
     pry
    0.23
    և
    0.23
    Activations Density 0.046%

    No Known Activations