Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13373
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those containing hexadecimal representations and array/struct definitions

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     CreateTagHelper
    -0.75
    ंदीखरीदारी
    -0.60
    anyar
    -0.59
    */),
    -0.59
    IsContent
    -0.56
    AddTagHelper
    -0.56
     متعلقه
    -0.56
    AddHtmlAttribute
    -0.54
     khiển
    -0.54
     mal
    -0.52
    POSITIVE LOGITS
    principalColumn
    0.63
    Composable
    0.59
    MethodManager
    0.57
    UIControlState
    0.55
    IContainer
    0.54
     []:
    0.53
    XtraReports
    0.52
     suivez
    0.51
    adaptiveStyles
    0.49
     caneca
    0.49
    Activations Density 18.854%

    No Known Activations