© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6272
    Prev
    Next
    INDEX
    Explanations

    I apologize, I appreciate, I see

    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_39_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
     тобой
    0.41
     indestructible
    0.40
    给你
    0.39
    矾
    0.38
     seller
    0.38
     ஆல்
    0.38
    Powerful
    0.37
    給你
    0.37
     kamu
    0.37
    ₵
    0.37
    POSITIVE LOGITS
     Aless
    0.38
     Wojcie
    0.38
     सदस्यीय
    0.36
    werken
    0.36
    uite
    0.35
    arrange
    0.35
    ensor
    0.35
     tass
    0.35
     स्पर्धा
    0.35
    htein
    0.35
    Activations Density 0.057%

    No Known Activations