© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201240
    Prev
    Next
    INDEX
    Explanations

    Rodeo Drive shopping

    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_12_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
    Binder
    0.58
     ଚ
    0.49
    ित्य
    0.48
    ٿ
    0.48
     Brushed
    0.46
    repositories
    0.46
    濩
    0.46
    해서
    0.45
    ijd
    0.45
    issam
    0.45
    POSITIVE LOGITS
    ”
    0.52
     imbalance
    0.51
     craving
    0.48
     turma
    0.47
     emptying
    0.46
     coût
    0.46
     costs
    0.46
    ாக்கு
    0.46
    ʺ
    0.45
     CNS
    0.44
    Activations Density 0.001%

    No Known Activations