© 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. 12426
    Prev
    Next
    INDEX
    Explanations

    words related to understanding and facts

    oai_token-act-pair · gemini-2.0-flash

    references to 'knowledge'

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

    knowledge

    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
    kuuta
    -0.50
     knowledge
    -0.48
     spo
    -0.46
    getFullYear
    -0.44
     transport
    -0.44
    PageModule
    -0.43
    transport
    -0.40
    Transport
    -0.39
    geen
    -0.39
    ia
    -0.38
    POSITIVE LOGITS
    InjectAttribute
    0.83
    WaitGroup
    0.79
     &___
    0.77
    Geplaatst
    0.75
    +#+#
    0.75
    исленность
    0.74
    elemField
    0.69
    tvguidetime
    0.69
    NavController
    0.68
    ThroughAttribute
    0.66
    Activations Density 1.949%

    No Known Activations