© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44691
    Prev
    Next
    INDEX
    Explanations

    Tetris

    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_3_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
    s
    0.99
    ne
    0.82
    S
    0.70
    C
    0.69
    st
    0.66
    Terminology
    0.66
    J
    0.66
    et
    0.65
    mel
    0.63
    \
    0.62
    POSITIVE LOGITS
     abierta
    0.68
     avantages
    0.68
     défis
    0.68
    น
    0.68
    ابي
    0.65
    ుల
    0.64
     Minist
    0.64
     cuadrada
    0.64
     dakika
    0.63
     tomate
    0.63
    Activations Density 0.002%

    No Known Activations