© 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. 33006
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     creș
    0.62
    рёх
    0.61
    ёт
    0.58
     ребён
    0.55
    ём
    0.55
    щё
    0.55
    Ș
    0.55
     ещё
    0.53
     чёр
    0.53
     трёх
    0.53
    POSITIVE LOGITS
    ㄉ
    0.58
     тощо
    0.54
    ﮭ
    0.52
    ㄧ
    0.52
    ㄑ
    0.51
    ㄋ
    0.50
    或是
    0.50
     vapour
    0.50
     এছাড়াও
    0.49
     tumour
    0.48
    Activations Density 0.020%

    No Known Activations