© 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. 43838
    Prev
    Next
    INDEX
    Explanations

    demureurge

    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
    (
    1.02
    5
    0.92
    4
    0.92
    '
    0.87
    1
    0.83
    ’
    0.77
    _
    0.76
    ׳
    0.74
     cataly
    0.71
    $\
    0.70
    POSITIVE LOGITS
    u
    0.66
    on
    0.64
    es
    0.64
    old
    0.62
    scenes
    0.58
    elés
    0.58
    is
    0.57
     λ
    0.57
    ového
    0.57
    o
    0.57
    Activations Density 0.002%

    No Known Activations