© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13243
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are used for emphasis or to connect ideas within text

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     الحره
    -0.53
    Alongside
    -0.53
     DAMAGES
    -0.52
    ůli
    -0.52
     ISNI
    -0.51
     contrário
    -0.50
     fiabilidad
    -0.49
     ;
    -0.49
     وتسجيلات
    -0.49
     dunque
    -0.49
    POSITIVE LOGITS
    LikeLiked
    0.65
    uxxxx
    0.64
    XmlEnum
    0.63
    GEBURTS
    0.59
    Individ
    0.59
     }{@
    0.58
     صوتيه
    0.56
    GraphicsUnit
    0.56
    .}\
    0.55
    AddHtmlAttribute
    0.52
    Activations Density 4.454%

    No Known Activations