© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4179
    Prev
    Next
    INDEX
    Explanations

    the word "flow" and related terms like "chart" and "process"

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to flowcharts and processes

    np_token-act-pair-logits · gpt-4o-mini

    flow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     fluid
    -0.44
    devamını
    -0.43
     classiques
    -0.42
     nélk
    -0.42
     Rodrigues
    -0.41
    baikan
    -0.41
    titure
    -0.40
     Paese
    -0.40
    ตร์
    -0.39
     alluminio
    -0.39
    POSITIVE LOGITS
    ThroughAttribute
    0.88
     дописавши
    0.70
    esModule
    0.68
     defaultstate
    0.67
    tagHelperRunner
    0.67
    RegressionTest
    0.65
    ruptedException
    0.65
    queryInterface
    0.64
    الحياه
    0.64
    oredCriteria
    0.63
    Activations Density 3.078%

    No Known Activations