© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 62379
    Prev
    Next
    INDEX
    Explanations

    endoplasmic reticulum

    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_41_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
    猢
    0.45
     informing
    0.40
     legislative
    0.40
     फॉ
    0.39
     /ˈ
    0.39
    קת
    0.37
    纖
    0.36
    羪
    0.36
     Legislative
    0.35
     Fonte
    0.35
    POSITIVE LOGITS
     ER
    1.02
     endoplasmic
    1.01
     rough
    0.75
     gol
    0.74
    ER
    0.73
     Golgi
    0.73
    Gol
    0.72
     er
    0.67
     Rough
    0.67
     reticulum
    0.66
    Activations Density 0.001%

    No Known Activations