© 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. 13922
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters and the character "Ž"

    oai_token-act-pair · gemini-2.0-flash

    the letter 'z' or similar shapes

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

    z

    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
     يتيمه
    -0.76
     CreateTagHelper
    -0.67
    ClientSize
    -0.62
    WithIOException
    -0.60
    tanleria
    -0.59
    CodedInputStream
    -0.58
    WireFormatLite
    -0.58
    شهاد
    -0.57
    DockStyle
    -0.56
    $_['
    -0.56
    POSITIVE LOGITS
    ровок
    0.55
     Montague
    0.53
     verke
    0.50
     ejus
    0.49
     Lel
    0.48
    uksessa
    0.48
     texinfo
    0.48
    principalColumn
    0.47
     conftest
    0.47
    ViewImports
    0.46
    Activations Density 0.102%

    No Known Activations