© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12345
    Prev
    Next
    INDEX
    Explanations

    a wide variety of seemingly disconnected phrases

    oai_token-act-pair · gemini-2.0-flash

    events/data analysis

    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
     виправивши
    -0.81
     تضيفلها
    -0.75
     gạch
    -0.68
    yntaxException
    -0.66
    EndGlobalSection
    -0.64
    Espèce
    -0.61
    Бахар
    -0.60
     yyb
    -0.60
    Smarty
    -0.59
    complexContent
    -0.59
    POSITIVE LOGITS
    ReadInt
    0.45
    oly
    0.44
    tot
    0.43
    ndor
    0.40
     Franklin
    0.40
    ionView
    0.40
    jiro
    0.38
     since
    0.38
    Franklin
    0.38
    jee
    0.37
    Activations Density 1.721%

    No Known Activations