© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86675
    Prev
    Next
    INDEX
    Explanations

    input placeholder text

    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_23_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
    CreateWindow
    0.40
     contextual
    0.40
    Chen
    0.38
    㧋
    0.37
     competición
    0.37
     スペ
    0.36
    Deposit
    0.35
    設施
    0.35
    䄱
    0.35
     강조
    0.35
    POSITIVE LOGITS
     Tunnel
    0.45
     Pharmac
    0.42
    Memory
    0.41
     Cheese
    0.40
     County
    0.40
    Ð
    0.39
     इंतजार
    0.39
     Regione
    0.39
     Whiskey
    0.38
     प्रमोद
    0.38
    Activations Density 0.000%

    No Known Activations