© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3470
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terms

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     клю
    -0.47
     dramatique
    -0.46
     costas
    -0.46
     supérieurs
    -0.45
     fermés
    -0.44
    print
    -0.44
     sva
    -0.43
     grandes
    -0.43
     not
    -0.43
    ↵↵↵↵
    -0.42
    POSITIVE LOGITS
     виправивши
    1.01
    DockStyle
    0.96
    MigrationBuilder
    0.86
    ChildScrollView
    0.81
    SharedDtor
    0.81
     MainAxisSize
    0.79
     BrowserModule
    0.77
     contextLoads
    0.76
    FormTagHelper
    0.75
     IBOutlet
    0.75
    Activations Density 8.433%

    No Known Activations