© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53475
    Prev
    Next
    INDEX
    Explanations

    for [time duration]

    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_30_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
    射
    0.42
    reg
    0.42
    squares
    0.38
    ”。
    0.37
    隷
    0.37
     allá
    0.37
    在你
    0.36
    ！」
    0.35
    !!”
    0.35
    enumer
    0.34
    POSITIVE LOGITS
    LocalizedString
    0.44
     ټول
    0.40
    жную
    0.39
     cooked
    0.38
    濁
    0.38
    ื้น
    0.38
     Voices
    0.38
     лока
    0.38
     извест
    0.38
     widowed
    0.37
    Activations Density 0.002%

    No Known Activations