© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18634
    Prev
    Next
    INDEX
    Explanations

    elegance, power, mystery

    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
    red
    0.58
     red
    0.49
     красный
    0.44
     darker
    0.44
     kırmızı
    0.43
    сті
    0.42
     крас
    0.42
    心
    0.42
     লাল
    0.41
    心が
    0.41
    POSITIVE LOGITS
     giảm
    0.40
     Reduce
    0.39
     mengurangi
    0.39
    Reduce
    0.38
    ྭ
    0.37
     DETER
    0.36
    㸳
    0.36
     Ew
    0.36
     reduce
    0.36
     deterrence
    0.36
    Activations Density 0.002%

    No Known Activations