© 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. 6416
    Prev
    Next
    INDEX
    Explanations

    words related to business transactions and sales, particularly in the automotive or marine industry

    oai_token-act-pair · gemini-2.0-flash

    words related to repair and maintenance

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

    repair

    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
    hoeddwyd
    -0.64
    Referințe
    -0.51
     فريبيس
    -0.51
    󠁢
    -0.50
    ActionCreators
    -0.50
     Athene
    -0.50
    coroutines
    -0.50
    enumii
    -0.50
     elevation
    -0.48
    ثيق
    -0.48
    POSITIVE LOGITS
     repair
    0.73
     workshop
    0.69
     Repair
    0.68
    repair
    0.67
     refin
    0.65
     workshops
    0.64
     repairs
    0.63
     Repairs
    0.63
     Workshop
    0.63
    Repair
    0.62
    Activations Density 2.077%

    No Known Activations