© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158174
    Prev
    Next
    INDEX
    Explanations

    sensation or whatsoever

    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_2_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
    ка
    1.22
    ра
    1.20
    ко
    1.09
    ك
    1.03
    ı
    1.02
    al
    1.02
    c
    1.01
    ាតុ
    1.00
    ",
    0.98
    ang
    0.97
    POSITIVE LOGITS
    ↵↵
    1.12
     conduct
    1.01
     weatherproof
    1.01
     coffin
    0.96
     ی
    0.94
     torpedo
    0.93
     laboratory
    0.93
     downside
    0.92
     whopping
    0.92
    یل
    0.91
    Activations Density 0.000%

    No Known Activations