© 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. 7453
    Prev
    Next
    INDEX
    Explanations

    numbers that may represent age or dates

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    SequentialGroup
    -0.45
     upp
    -0.43
    ira
    -0.43
     oper
    -0.42
     full
    -0.39
    Petro
    -0.39
    mycompany
    -0.39
     חיצוניים
    -0.39
    HasAnnotation
    -0.38
    onto
    -0.38
    POSITIVE LOGITS
     متعلقه
    0.76
     تضيفلها
    0.75
    NewUrlParser
    0.69
     Réponses
    0.68
    Tikang
    0.66
     समीक्षाओं
    0.65
     kasarigan
    0.64
    UrlResolution
    0.64
     JpaRepository
    0.63
    وفاته
    0.62
    Activations Density 1.435%

    No Known Activations