© 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. 206476
    Prev
    Next
    INDEX
    Explanations

    supply last worth

    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
     betrayed
    0.52
     c
    0.47
     couldn
    0.47
     ‘
    0.46
     ห
    0.46
     betray
    0.46
     thinks
    0.46
    think
    0.45
    vio
    0.44
     violated
    0.43
    POSITIVE LOGITS
    仄
    0.59
    രിച്ച്
    0.50
    笈
    0.48
    ارڈ
    0.46
    ებში
    0.45
    Arvore
    0.45
    DeferredGroup
    0.45
    ואר
    0.44
    >≤</
    0.43
    선의
    0.43
    Activations Density 0.000%

    No Known Activations