© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9852
    Prev
    Next
    INDEX
    Explanations

    pieces of programming code rather than natural language

    oai_token-act-pair · gemini-2.0-flash

    Javascript variable declaration

    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
     يتيمه
    -0.57
     BoxFit
    -0.53
    reactivex
    -0.53
     čaj
    -0.53
    出版年
    -0.53
    enumi
    -0.52
    +#+#
    -0.52
     petto
    -0.51
     kağıt
    -0.50
    TextEditing
    -0.49
    POSITIVE LOGITS
     OBITUARY
    0.60
     Италијани
    0.59
     mine
    0.57
    tanleria
    0.57
    ώρα
    0.56
     op
    0.56
    ristiana
    0.55
    roxene
    0.54
    messageInfo
    0.54
    alada
    0.54
    Activations Density 1.997%

    No Known Activations