© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10581
    Prev
    Next
    INDEX
    Explanations

    code syntax, including words like "public", "private", "class", datatypes and symbols like [, ], (, ), :, and =

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    Tikang
    -0.71
     pleaſure
    -0.69
     AssemblyVersion
    -0.68
     végétale
    -0.68
     uſe
    -0.62
     ویکی‌پدی
    -0.62
     définiti
    -0.61
     anhydride
    -0.61
     purpoſe
    -0.60
    ValueStyle
    -0.60
    POSITIVE LOGITS
    SourceChecksum
    0.55
     IActionResult
    0.48
    posh
    0.43
    ocino
    0.43
     ModelExpression
    0.43
     Photocase
    0.39
     Rend
    0.39
    ":"",
    0.38
    INSEE
    0.38
    ণ
    0.38
    Activations Density 0.587%

    No Known Activations