© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1549
    Prev
    Next
    INDEX
    Explanations

    words related to technical performance and processes

    oai_token-act-pair · gemini-2.0-flash

    product feature descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    lorette
    -0.65
    AndEndTag
    -0.61
    ziplin
    -0.57
     nakalista
    -0.57
    InputBorder
    -0.57
    fromnode
    -0.55
     الاطلاع
    -0.54
    GenerationType
    -0.54
    :]:
    -0.54
     Baillargeon
    -0.54
    POSITIVE LOGITS
    EndGlobalSection
    0.53
     paired
    0.53
    IndentedString
    0.52
     despite
    0.52
    capabilities
    0.52
     provided
    0.52
    RegressionTest
    0.50
     bacio
    0.50
     imparted
    0.50
    dataclass
    0.50
    Activations Density 5.862%

    No Known Activations