© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5720
    Prev
    Next
    INDEX
    Explanations

    code and names of Chinese people and places

    oai_token-act-pair · gemini-2.0-flash

    code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     '\\;'
    -0.52
     Kích
    -0.52
    IGraphics
    -0.49
    bumps
    -0.46
    aarrggbb
    -0.46
    DebuggerStep
    -0.46
     Lagoon
    -0.45
    InsertCommand
    -0.44
    ytale
    -0.43
    EndGlobalSection
    -0.43
    POSITIVE LOGITS
     jennifer
    0.55
     Eleanor
    0.55
    Cindy
    0.54
     ब्रेकडाउन
    0.52
    Cathy
    0.52
    Katherine
    0.52
    Gina
    0.51
    Angelina
    0.51
     Gina
    0.50
    原始内容存档于
    0.50
    Activations Density 1.703%

    No Known Activations