© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    technical and medical jargon involving users, patients, operators, and researchers

    oai_token-act-pair · gemini-2.0-flash

    non-standard identifiers or technical terms

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

    user

    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
    who
    -0.61
     Quien
    -0.60
    whom
    -0.58
     quien
    -0.51
    пьютер
    -0.51
    úgó
    -0.51
     chapa
    -0.50
     Who
    -0.47
    Who
    -0.47
    umented
    -0.46
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    1.00
     nahilalakip
    0.81
    XtraReports
    0.70
     resourceCulture
    0.66
     مرئيه
    0.61
    HomeAsUp
    0.58
    \{\\
    0.56
    허
    0.55
     Tenggara
    0.55
    BitConverter
    0.54
    Activations Density 4.522%

    No Known Activations