© 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. 34032
    Prev
    Next
    INDEX
    Explanations

    laying down

    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
    j
    0.89
    ü
    0.83
    :
    0.81
    '
    0.80
    ä
    0.80
    re
    0.75
     can
    0.75
     It
    0.74
    can
    0.72
    0.72
    POSITIVE LOGITS
    дә
    0.74
    čiti
    0.73
    ים
    0.68
    ৎ
    0.68
    ین
    0.67
    ンダ
    0.67
    વાની
    0.65
    ザ
    0.64
    ುವುದ
    0.64
    یف
    0.64
    Activations Density 0.001%

    No Known Activations