© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 301
    Prev
    Next
    INDEX
    Explanations

    information about animation, art, and/or expertise

    oai_token-act-pair · gemini-2.0-flash

    Education and websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    苔
    -0.49
     Ausgleich
    -0.47
     croire
    -0.46
    waard
    -0.46
    tum
    -0.43
    inai
    -0.43
    خر
    -0.42
    ONSO
    -0.42
    versal
    -0.42
     whims
    -0.41
    POSITIVE LOGITS
     <=",
    1.05
    InitVars
    0.83
     >=",
    0.82
     itſelf
    0.81
    AsUp
    0.81
     Efq
    0.80
     Jefus
    0.79
    IUrlHelper
    0.79
     للاسماء
    0.77
     referenties
    0.77
    Activations Density 1.819%

    No Known Activations