© 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. 2016
    Prev
    Next
    INDEX
    Explanations

    Arabic names and news organizations

    oai_token-act-pair · gemini-2.0-flash

    terms related to organization names or entities

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

    Arabic context

    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
    GOTREF
    -0.55
     C
    -0.50
     free
    -0.48
    pinMode
    -0.48
     payment
    -0.46
    dorff
    -0.46
     pull
    -0.45
     免费
    -0.44
     Free
    -0.44
    emic
    -0.44
    POSITIVE LOGITS
    IUrlHelper
    0.78
    Personensuche
    0.68
     AssemblyCompany
    0.62
     jScrollPane
    0.62
    contentLoaded
    0.61
    WriteLiteral
    0.60
     propOrder
    0.60
    sizeCache
    0.59
    IsMutable
    0.59
     peine
    0.59
    Activations Density 0.408%

    No Known Activations