© 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. 570
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to customers using computer applications to order products from vendors

    oai_token-act-pair · gemini-2.0-flash

    software and systems

    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
     فريبيس
    -0.81
    DoubleQuotes
    -0.66
     ControllerBase
    -0.65
    WireFormat
    -0.60
     ويكيميديا
    -0.58
    rungsseite
    -0.56
    posedge
    -0.55
     userManager
    -0.54
    %
    -0.53
    Administ
    -0.52
    POSITIVE LOGITS
     produisons
    0.56
     lenker
    0.55
    Хьажоргаш
    0.55
     internacionais
    0.54
     médié
    0.53
     CITED
    0.52
     solares
    0.52
    MigrationBuilder
    0.50
     réelle
    0.50
     Jerusalén
    0.49
    Activations Density 1.172%

    No Known Activations