© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7075
    Prev
    Next
    INDEX
    Explanations

    mentions of team names, logos, and uniforms for sports teams

    oai_token-act-pair · gemini-2.0-flash

    words related to marking or labeling

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

    Names, marks, wording

    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
    migrationBuilder
    -0.96
    AndEndTag
    -0.82
     ivelany
    -0.81
     <>",
    -0.69
    رشف
    -0.68
    addCriterion
    -0.63
     دیکھیے
    -0.62
    ánto
    -0.61
    Diweddarwch
    -0.60
    BeginContext
    -0.58
    POSITIVE LOGITS
     mark
    0.60
     words
    0.59
    mark
    0.59
     word
    0.55
    マーク
    0.51
    
    0.51
     wording
    0.51
     marks
    0.50
     name
    0.50
    marks
    0.48
    Activations Density 2.667%

    No Known Activations