© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132442
    Prev
    Next
    INDEX
    Explanations

    teleport

    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_1_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
    ס
    1.70
    ir
    1.40
    ור
    1.38
    .
    1.36
    מ
    1.33
    ot
    1.27
    м
    1.25
    い
    1.21
    म
    1.18
    с
    1.16
    POSITIVE LOGITS
     و
    0.96
    䛛
    0.95
    uhan
    0.92
    呎
    0.91
    u
    0.89
    atches
    0.88
    人士
    0.88
    pción
    0.88
    ttes
    0.86
    fält
    0.85
    Activations Density 0.002%

    No Known Activations