© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62707
    Prev
    Next
    INDEX
    Explanations

    me

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     o
    0.99
     о
    0.96
     ا
    0.74
     ο
    0.65
     što
    0.52
     오
    0.52
     čo
    0.52
     what
    0.51
    何
    0.51
     օ
    0.49
    POSITIVE LOGITS
     When
    0.78
    When
    0.76
     WHEN
    0.62
     when
    0.61
     Concerning
    0.59
    Concerning
    0.54
     concerning
    0.54
    when
    0.53
    Cuando
    0.51
     Ketika
    0.51
    Activations Density 0.012%

    No Known Activations