© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166759
    Prev
    Next
    INDEX
    Explanations

    Il or il

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Occ
    0.41
     Occ
    0.41
     “
    0.40
    ocrats
    0.40
    रित
    0.40
     Terre
    0.38
    OCC
    0.38
    Cr
    0.38
    Wind
    0.38
    วจ
    0.38
    POSITIVE LOGITS
     annuelle
    0.41
    耄
    0.39
     nettoyage
    0.38
    늡
    0.37
     Remembering
    0.37
     ChangeNotifier
    0.37
    sley
    0.37
     biais
    0.37
    itif
    0.36
    غیر
    0.36
    Activations Density 0.000%

    No Known Activations