© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9297
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to locations and institutions

    oai_token-act-pair · gemini-2.0-flash

    named places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     rival
    -0.62
     Bailly
    -0.55
    ]+$
    -0.53
    omock
    -0.53
     geslacht
    -0.52
    ละ
    -0.51
    )))))
    -0.51
    iolis
    -0.50
    gridy
    -0.50
    rival
    -0.50
    POSITIVE LOGITS
    TargetException
    0.70
     OFDb
    0.66
    kuuta
    0.65
    
    0.63
    DoubleQuotes
    0.62
    UrlResolution
    0.58
    AndEndTag
    0.57
    TableHead
    0.57
    MeasureSpec
    0.56
    CodeAttribute
    0.54
    Activations Density 1.840%

    No Known Activations