© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26924
    Prev
    Next
    INDEX
    Explanations

    full name

    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_10_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
    িলার
    0.62
    ίζεται
    0.61
    리
    0.61
    colour
    0.60
    یم
    0.59
    نوع
    0.58
    Ꮺ
    0.57
    erre
    0.57
    ुल
    0.57
    s
    0.56
    POSITIVE LOGITS
    th
    0.72
    _
    0.70
     vuttam
    0.69
    м
    0.68
    AV
    0.66
     mai
    0.65
     piy
    0.64
    ☢
    0.64
     twor
    0.63
     tais
    0.63
    Activations Density 0.002%

    No Known Activations