© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    words related to sports statistics and play

    oai_token-act-pair · gemini-2.0-flash

    foreign names/code

    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
    Geplaatst
    -0.56
     QtWidgets
    -0.55
    TagHelpers
    -0.55
    Spoljašnje
    -0.54
    )<<
    -0.53
    RunWith
    -0.53
    adple
    -0.52
    enumi
    -0.52
    Vidite
    -0.51
     tslint
    -0.51
    POSITIVE LOGITS
    CppCodeGen
    0.53
     elétrico
    0.52
     Vikipedi
    0.51
    ATOS
    0.51
     Mue
    0.50
    gráfica
    0.50
    VIAF
    0.49
    Binds
    0.48
     Netto
    0.46
    newBuilder
    0.46
    Activations Density 0.978%

    No Known Activations