© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    calendar dates and religious terms, specifically related to Narashima Jayanthi

    oai_token-act-pair · gemini-2.0-flash

    specific names or terms

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

    festival celebrations

    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
     CreateTagHelper
    -0.75
    клопе
    -0.73
     للاسماء
    -0.73
    Autoritní
    -0.70
    ⓧ
    -0.68
     Theſe
    -0.67
    ](#
    -0.67
     שוליים
    -0.66
    AsUp
    -0.66
     réessayer
    -0.65
    POSITIVE LOGITS
    mybatisplus
    0.46
    chyma
    0.45
     vrou
    0.44
     Taktlose
    0.44
     vermo
    0.42
    che
    0.41
    št
    0.41
     curbs
    0.41
    ولی
    0.40
     fruiting
    0.40
    Activations Density 0.669%

    No Known Activations