© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3569
    Prev
    Next
    INDEX
    Explanations

    terms related to data visualization and network analysis

    oai_token-act-pair · gemini-2.0-flash

    networks and diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    enderror
    -0.67
     برانيه
    -0.62
    )|^{
    -0.56
    Pautan
    -0.56
    CodeAttribute
    -0.53
    LookAnd
    -0.50
    invokeLater
    -0.50
    DockStyle
    -0.50
    TagHelper
    -0.49
    awaiter
    -0.49
    POSITIVE LOGITS
     beginnetje
    0.63
     userSchema
    0.60
    liosis
    0.56
     estekak
    0.56
    jalá
    0.54
     mukana
    0.53
    كويكب
    0.53
    mặt
    0.53
    وفاته
    0.51
     diagrams
    0.51
    Activations Density 5.319%

    No Known Activations