© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195308
    Prev
    Next
    INDEX
    Explanations

    years old

    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_27_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
     belated
    0.54
     delayed
    0.53
    遅
    0.51
     retras
    0.47
    遲
    0.47
     postpone
    0.46
     tard
    0.45
     postponed
    0.45
     Delayed
    0.45
    Delayed
    0.45
    POSITIVE LOGITS
    ṕ
    0.40
    Bec
    0.39
    ष्टमी
    0.39
     intensification
    0.39
    ꩡ
    0.38
     comuna
    0.37
    യോഗ
    0.37
    年には
    0.37
     მათ
    0.36
    さんも
    0.36
    Activations Density 0.012%

    No Known Activations