© 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. 4445
    Prev
    Next
    INDEX
    Explanations

    the names of people from the middle east and surrounding areas

    oai_token-act-pair · gemini-2.0-flash

    prefixes related to names or titles

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

    Arabic article "al"

    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
     '\\;'
    -1.06
    Vidite
    -0.97
    DockStyle
    -0.96
    RTEX
    -0.88
    клопе
    -0.86
    ագրություններ
    -0.86
     مشين
    -0.82
    EndContext
    -0.82
    AccessorTable
    -0.80
     Wiktionnaire
    -0.79
    POSITIVE LOGITS
     al
    1.02
     el
    0.76
     Al
    0.70
    Al
    0.56
     El
    0.55
     аль
    0.53
     AL
    0.52
     ad
    0.52
    ul
    0.52
     es
    0.51
    Activations Density 1.363%

    No Known Activations