© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8331
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to file systems, especially within Java

    oai_token-act-pair · gemini-2.0-flash

    System

    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
     system
    -1.19
     systems
    -1.12
     System
    -1.09
    system
    -1.09
     SYSTEM
    -1.02
    System
    -1.01
    systems
    -0.97
     sys
    -0.94
     sistem
    -0.92
     Systems
    -0.90
    POSITIVE LOGITS
    .
    0.63
     tetrachloride
    0.41
    Err
    0.40
    СТА
    0.40
     évaluations
    0.40
     idé
    0.40
     Dresses
    0.39
     catalana
    0.39
     Wre
    0.39
     Madness
    0.39
    Activations Density 1.746%

    No Known Activations