© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4085
    Prev
    Next
    INDEX
    Explanations

    the word "repeat" with some additional emphasis on words related to arrays, options, and small towns

    oai_token-act-pair · gemini-2.0-flash

    repeat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tich
    -0.56
    HomeAsUp
    -0.56
     ihtiyac
    -0.52
    IGraphics
    -0.52
     sebaliknya
    -0.51
    ATIVA
    -0.51
    TG
    -0.50
     SC
    -0.50
     AttributeSet
    -0.50
    gliere
    -0.49
    POSITIVE LOGITS
    <bos>
    1.74
    Personensuche
    0.81
    مصادر
    0.79
     nahilalakip
    0.78
     auffi
    0.71
    SpringRunner
    0.71
    IUrlHelper
    0.69
     noDo
    0.68
    Дереккөздер
    0.68
    Билгалдахарш
    0.66
    Activations Density 2.359%

    No Known Activations