© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13288
    Prev
    Next
    INDEX
    Explanations

    proper nouns with associated punctuation

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     maten
    -0.44
     Ron
    -0.43
    Speakers
    -0.43
    ாய
    -0.43
     heridas
    -0.43
     pessoais
    -0.42
     Eisen
    -0.42
     Speakers
    -0.40
     Offensive
    -0.40
    ngOnInit
    -0.40
    POSITIVE LOGITS
     protoimpl
    0.82
    tagHelperRunner
    0.77
    LookAnd
    0.69
    ImageContext
    0.68
     AssemblyProduct
    0.67
     initComponents
    0.66
    "]);
    0.66
     发表于
    0.66
    "])
    0.65
    migrationBuilder
    0.64
    Activations Density 0.442%

    No Known Activations