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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11691
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing restaurants and supermarkets and their merchandise

    oai_token-act-pair · gemini-2.0-flash

    references to general or broad categories

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

    supermarkets and shopping related text

    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
     Roskov
    -0.72
    Искәрмәләр
    -0.70
     AssemblyCulture
    -0.69
     endblock
    -0.61
     propOrder
    -0.61
     ModelExpression
    -0.59
    writeField
    -0.57
    EndGlobalSection
    -0.57
    ScopeManager
    -0.57
     beschik
    -0.57
    POSITIVE LOGITS
     general
    0.60
     General
    0.53
     الخ
    0.52
    general
    0.50
    General
    0.49
     hardware
    0.47
    tempted
    0.44
    eventbus
    0.44
     emp
    0.44
     Active
    0.44
    Activations Density 0.827%

    No Known Activations