© 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. 2736
    Prev
    Next
    INDEX
    Explanations

    explanation of why

    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
     amour
    0.38
     eso
    0.38
     김
    0.38
     kim
    0.37
     simplement
    0.37
     Please
    0.36
     Kimura
    0.36
     இவற்றை
    0.36
    Entonces
    0.36
     KIM
    0.36
    POSITIVE LOGITS
     PARTS
    0.38
     interacted
    0.38
    וחות
    0.38
    儷
    0.37
    yc
    0.36
     byli
    0.36
    ᵍ
    0.36
    istik
    0.35
    跡
    0.35
     οι
    0.35
    Activations Density 0.275%

    No Known Activations