© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially class and variable names

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ")->
    -0.51
    ))->
    -0.46
    ")));
    -0.45
    värr
    -0.43
     fler
    -0.42
     useRouter
    -0.42
    gjenge
    -0.42
    ())));
    -0.41
     antes
    -0.40
     Alexei
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.93
    +#+
    0.84
     cherchés
    0.75
     مشين
    0.71
    DoubleQuotes
    0.71
    tagHelperRunner
    0.68
     FetchType
    0.63
     onPostExecute
    0.63
    CppMethod
    0.61
     MongoClient
    0.60
    Activations Density 41.253%

    No Known Activations