© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198409
    Prev
    Next
    INDEX
    Explanations

    busy

    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_15_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
     funzionalità
    0.36
     WORKS
    0.36
     работы
    0.34
     comentários
    0.34
     comentário
    0.34
     AUTHORITY
    0.33
     имају
    0.32
     '}
    0.32
    )}.
    0.32
     özellikleri
    0.32
    POSITIVE LOGITS
    、
    0.40
    اد
    0.36
    べき
    0.33
    purs
    0.32
    ώντας
    0.31
     distracted
    0.31
     greed
    0.30
     scorso
    0.30
    eka
    0.30
    ีน
    0.30
    Activations Density 0.057%

    No Known Activations