© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137164
    Prev
    Next
    INDEX
    Explanations

    honey or maple syrup drizzle

    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_12_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
     meditations
    0.55
     oatmeal
    0.55
     Oatmeal
    0.51
     audioElement
    0.50
     аудио
    0.49
     avocados
    0.49
    揸
    0.49
     thoughts
    0.49
     seroton
    0.49
    termilk
    0.48
    POSITIVE LOGITS
     q
    0.49
    autista
    0.49
     lze
    0.48
    ათ
    0.48
    ால்
    0.47
    ߋ
    0.46
    went
    0.46
    an
    0.45
     lancé
    0.45
     Jeux
    0.45
    Activations Density 0.002%

    No Known Activations