© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13960
    Prev
    Next
    INDEX
    Explanations

    text that resembles questions, coding instructions, or answers on online discussion forums

    oai_token-act-pair · gemini-2.0-flash

    non-English or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    naeus
    -0.52
    یاد
    -0.50
    íncia
    -0.49
    ábamos
    -0.48
    LookAnd
    -0.48
    DMETHOD
    -0.47
     виправивши
    -0.47
    大山
    -0.47
    isOk
    -0.46
     sẻ
    -0.45
    POSITIVE LOGITS
     jesu
    0.56
    setViewportView
    0.55
    AddHtmlAttribute
    0.52
    webElementGuid
    0.51
    URLException
    0.49
    BeginContext
    0.49
     Silvio
    0.48
     conftest
    0.48
    Przypisy
    0.48
     gql
    0.48
    Activations Density 0.531%

    No Known Activations