© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75218
    Prev
    Next
    INDEX
    Explanations

    scientists don't trust atoms

    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_31_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
     paired
    0.40
    ᓗ
    0.40
    强调
    0.38
    പ്പം
    0.38
     work
    0.37
    強調
    0.37
    coupled
    0.37
    上
    0.36
     ща
    0.36
     arbejde
    0.35
    POSITIVE LOGITS
    メモ
    0.47
     vertrou
    0.43
     страш
    0.42
    酔
    0.42
     bezpeč
    0.41
     güven
    0.39
     дове
    0.39
     सेफ्टी
    0.39
     믿
    0.39
     грамо
    0.38
    Activations Density 0.001%

    No Known Activations