© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2774
    Prev
    Next
    INDEX
    Explanations

    undertake / taken / understood

    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_40_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
    íveis
    0.37
     Established
    0.37
    uée
    0.37
     跳
    0.36
    ಂದು
    0.34
    वंशी
    0.34
    䢙
    0.34
    Established
    0.34
    ואה
    0.33
    參
    0.33
    POSITIVE LOGITS
     taken
    0.95
    taken
    0.92
    取
    0.87
     Taken
    0.86
    Taken
    0.85
     taking
    0.83
    取り
    0.83
    taking
    0.82
     taker
    0.81
     취
    0.80
    Activations Density 0.012%

    No Known Activations