© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12141
    Prev
    Next
    INDEX
    Explanations

    mentions of the season "summer" and words that occur near "summer"

    oai_token-act-pair · gemini-2.0-flash

    summer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    LookAnd
    -1.03
    AndEndTag
    -0.82
    CppMethod
    -0.79
     AssemblyCulture
    -0.75
     unknownFields
    -0.74
    OrBuilder
    -0.74
    QMetaType
    -0.73
    ContentAsync
    -0.65
    WriteTagHelper
    -0.65
    webElementXpaths
    -0.65
    POSITIVE LOGITS
    ividual
    0.79
    vrolet
    0.77
    frastructure
    0.77
    edded
    0.77
     pleaſure
    0.75
    ousand
    0.73
    LOYE
    0.72
    ſelf
    0.69
    virons
    0.69
    terday
    0.69
    Activations Density 2.650%

    No Known Activations