© 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. 44182
    Prev
    Next
    INDEX
    Explanations

    languages question words

    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
    ir
    1.15
    es
    1.10
    t
    1.10
    5
    1.09
    9
    1.05
    1
    1.00
    ant
    0.99
    6
    0.97
    ed
    0.95
    4
    0.92
    POSITIVE LOGITS
     knowingly
    0.83
     is
    0.81
     conoscenza
    0.78
     и
    0.76
     ו
    0.76
    ك
    0.76
    す
    0.75
     և
    0.73
     conocidas
    0.72
     знают
    0.71
    Activations Density 0.003%

    No Known Activations