© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195776
    Prev
    Next
    INDEX
    Explanations

    Coca-Cola

    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_4_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
    5
    1.58
    7
    1.51
    9
    1.39
    6
    1.37
    3
    1.31
    8
    1.31
    4
    1.30
    و
    1.27
    2
    1.25
    </h2>
    1.24
    POSITIVE LOGITS
    t
    1.25
    al
    1.06
    '
    1.04
    h
    0.96
    х
    0.92
    olja
    0.87
    alag
    0.84
    ’
    0.79
    alir
    0.77
    inat
    0.75
    Activations Density 0.002%

    No Known Activations