© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209625
    Prev
    Next
    INDEX
    Explanations

    passion for fields and activities

    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_20_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
     restraints
    0.38
    外
    0.38
     Bộ
    0.37
    où
    0.37
    雨
    0.36
    Bộ
    0.36
     Buxton
    0.36
    rainte
    0.35
     Heavy
    0.34
    ordinate
    0.34
    POSITIVE LOGITS
     интернет
    0.39
    អ៊ី
    0.39
     intelligents
    0.39
     އި
    0.39
     expands
    0.38
     인터넷
    0.38
     పరిశ
    0.37
     celular
    0.37
     ސ
    0.37
     celulares
    0.37
    Activations Density 0.002%

    No Known Activations