© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2894
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate a conceptual relationship or connection

    oai_token-act-pair · gemini-2.0-flash

    inherent attributes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    حياتها
    -0.66
    حياته
    -0.61
    principalTable
    -0.57
     ostavi
    -0.53
     Aws
    -0.52
     Oakes
    -0.52
    >{@
    -0.50
    tily
    -0.50
    reuung
    -0.49
     censiti
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.78
    httphttps
    0.61
    sidemargin
    0.54
     beginnetje
    0.50
     linkovi
    0.49
    Texte
    0.49
    RectangleBorder
    0.49
    تقاوى
    0.45
    bootstrapcdn
    0.45
    ORUS
    0.45
    Activations Density 4.044%

    No Known Activations