© 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. 203256
    Prev
    Next
    INDEX
    Explanations

    became apparent that

    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
    t
    0.70
     first
    0.63
     from
    0.62
     participle
    0.61
     as
    0.59
     off
    0.59
    v
    0.59
     exam
    0.59
     last
    0.58
     early
    0.57
    POSITIVE LOGITS
     keperluan
    0.59
    ться
    0.57
     atau
    0.52
     شود
    0.52
     Vive
    0.52
     或
    0.52
     ойноо
    0.51
     качество
    0.51
    haal
    0.50
    henti
    0.50
    Activations Density 0.000%

    No Known Activations