© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14800
    Prev
    Next
    INDEX
    Explanations

    text related to financial markets and business descriptions

    oai_token-act-pair · gemini-2.0-flash

    global companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ItemBackground
    -0.73
    shadowOffset
    -0.66
    IndentedString
    -0.66
    ftagPool
    -0.60
    loài
    -0.54
    Portale
    -0.53
     typelib
    -0.53
    Hentet
    -0.52
    roek
    -0.52
    HostException
    -0.51
    POSITIVE LOGITS
    DoubleQuotes
    0.55
    例文
    0.49
     khảo
    0.48
     juridiques
    0.47
    systems
    0.47
     SYSTEMS
    0.47
     bên
    0.47
     sahiptir
    0.46
     touche
    0.46
     poichè
    0.45
    Activations Density 9.362%

    No Known Activations