© 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
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260665
    Prev
    Next
    INDEX
    Explanations

    encrypt, encircle

    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_22_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
     durchaus
    0.36
    valu
    0.35
    اعه
    0.35
     Gén
    0.34
    queens
    0.33
    귿
    0.33
    webstore
    0.33
     മേഖല
    0.33
     குறை
    0.33
     العمليه
    0.33
    POSITIVE LOGITS
     bacteri
    0.37
    ‵
    0.36
     reed
    0.36
     Chai
    0.36
     ибо
    0.36
     argon
    0.34
    argon
    0.34
     indetermin
    0.34
     выдви
    0.34
     prefab
    0.34
    Activations Density 0.000%

    No Known Activations