© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209808
    Prev
    Next
    INDEX
    Explanations

    connectors and pins

    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_10_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
    س
    0.91
    ਕ
    0.82
    ק
    0.80
    م
    0.79
    א
    0.78
    ك
    0.78
    на
    0.77
    יש
    0.76
    在
    0.75
    ক
    0.74
    POSITIVE LOGITS
     জনাব
    0.63
     জড়
    0.63
     Annals
    0.63
    il
    0.60
    ray
    0.60
     N
    0.58
    ст
    0.58
    and
    0.57
     Phó
    0.57
     Nauk
    0.57
    Activations Density 0.002%

    No Known Activations