© 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. 10584
    Prev
    Next
    INDEX
    Explanations

    words related to shopping and product properties

    oai_token-act-pair · gemini-2.0-flash

    uncommon terms or specialized vocabulary

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

    technical contexts

    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
     among
    -2.22
    among
    -2.19
     Among
    -1.86
     amongst
    -1.84
     AMONG
    -1.80
    Among
    -1.77
     parmi
    -1.66
     Amongst
    -1.62
     blant
    -1.28
     среди
    -1.25
    POSITIVE LOGITS
     فريبيس
    0.83
    styleable
    0.81
    ScopeManager
    0.80
     ModelExpression
    0.73
    @[+][
    0.73
     Efq
    0.71
     Roskov
    0.68
    bkz
    0.66
     estekak
    0.65
    تقاوى
    0.65
    Activations Density 1.074%

    No Known Activations