© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5320
    Prev
    Next
    INDEX
    Explanations

    special characters and diacritics from various languages, including mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    multilingual text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Παραπομπές
    -0.70
    WebServlet
    -0.66
    invokeLater
    -0.64
     NSCoder
    -0.63
    Hole
    -0.58
    ResumeLayout
    -0.56
    DataPropertyName
    -0.54
     Normdatei
    -0.53
    IsContent
    -0.53
    fromCharCode
    -0.52
    POSITIVE LOGITS
    ۪
    0.53
     Hove
    0.46
    Estar
    0.46
     Novgorod
    0.46
    Distribución
    0.46
    Distribuzione
    0.46
    hlen
    0.46
    randomUUID
    0.45
     aceptas
    0.45
    تأ
    0.44
    Activations Density 0.692%

    No Known Activations