© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12828
    Prev
    Next
    INDEX
    Explanations

    varied concepts, including rural/Southern US imagery, violent or sexual movie imagery, and images of poverty and charity in Africa.

    oai_token-act-pair · gemini-2.0-flash

    scenery and/or theater

    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
     magasiner
    -0.45
    UpInside
    -0.44
    
    -0.43
     OFDb
    -0.42
    avanje
    -0.42
     censi
    -0.42
     high
    -0.41
    bufio
    -0.41
    ATHER
    -0.41
     classroom
    -0.41
    POSITIVE LOGITS
    FormTagHelper
    0.79
    InstrumentedTest
    0.76
     CreateTagHelper
    0.68
    SharedDtor
    0.66
    gameserver
    0.65
    AccessorTable
    0.63
     uſed
    0.63
     resourceCulture
    0.57
    localctx
    0.57
    #+#
    0.57
    Activations Density 1.399%

    No Known Activations