© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126352
    Prev
    Next
    INDEX
    Explanations

    Haley or corpus then Python code

    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_3_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
     is
    1.43
     on
    0.93
     as
    0.91
     will
    0.90
     of
    0.86
     has
    0.79
    0.78
     are
    0.75
     .
    0.73
     can
    0.71
    POSITIVE LOGITS
    ्ह
    0.64
     Dahmer
    0.61
    ्या
    0.60
    ulet
    0.59
     repris
    0.59
    resses
    0.59
    <
    0.59
    Ŭ
    0.59
    ็น
    0.58
    ्ज
    0.57
    Activations Density 0.000%

    No Known Activations