© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124882
    Prev
    Next
    INDEX
    Explanations

    Pinkman, Owens, Marcel, Watters

    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
     that
    0.71
    ли
    0.71
     que
    0.67
    다
    0.65
     (
    0.64
     musica
    0.60
    त
    0.59
     will
    0.58
    ματα
    0.58
    ться
    0.58
    POSITIVE LOGITS
    d
    0.84
    b
    0.73
    m
    0.70
    matt
    0.66
    w
    0.66
     Cleaning
    0.61
    v
    0.61
    rolls
    0.59
    winning
    0.58
    pg
    0.57
    Activations Density 0.000%

    No Known Activations