© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13933
    Prev
    Next
    INDEX
    Explanations

    code in Portuguese that changes players in a tic-tac-toe game

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pitié
    -0.75
     cref
    -0.74
     Theſe
    -0.73
     démocr
    -0.70
    itself
    -0.70
     umana
    -0.69
     Cæsar
    -0.69
     Efq
    -0.69
     scolaires
    -0.68
     canst
    -0.68
    POSITIVE LOGITS
     fine
    0.53
     Paglinawan
    0.42
     said
    0.40
     Fine
    0.39
     que
    0.37
    ArgumentParser
    0.37
    protoimpl
    0.35
    fine
    0.35
    styleType
    0.35
    周
    0.34
    Activations Density 0.765%

    No Known Activations