© 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. 14104
    Prev
    Next
    INDEX
    Explanations

    snippets of code, especially in python with the term 'self'

    oai_token-act-pair · gemini-2.0-flash

    foreign words/code

    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
    .
    -0.54
     return
    -0.47
    7
    -0.47
     SHE
    -0.44
    ,
    -0.44
    ↵
    -0.43
     und
    -0.42
    She
    -0.41
    ányi
    -0.41
     London
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.81
    extAlignment
    0.80
     '\\;'
    0.79
     للمعارف
    0.78
     myſelf
    0.76
    NUMX
    0.75
     Theſe
    0.75
    Portale
    0.74
    ✨:
    0.73
    ValueStyle
    0.72
    Activations Density 1.800%

    No Known Activations