© 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. 43727
    Prev
    Next
    INDEX
    Explanations

    psql

    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
    i
    1.36
    l
    1.08
    d
    1.06
    t
    0.96
    e
    0.95
    ta
    0.94
    b
    0.91
    ar
    0.91
    y
    0.90
    an
    0.89
    POSITIVE LOGITS
    考え
    1.02
    ка
    0.87
    それ
    0.79
    ك
    0.77
    無い
    0.75
    اہم
    0.75
     heures
    0.74
    ┳
    0.74
    リ
    0.73
    󰡔
    0.72
    Activations Density 0.000%

    No Known Activations