© 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. 2148
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are indicators of possession

    oai_token-act-pair · gemini-2.0-flash

    s

    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
    SequentialGroup
    -0.77
    abetes
    -0.65
     typelib
    -0.64
    ंदीखरीदारी
    -0.61
    LookAnd
    -0.61
     صوتيه
    -0.58
    NameInMap
    -0.58
     ویکی‌پدیا
    -0.57
    ⓧ
    -0.56
    GOTREF
    -0.56
    POSITIVE LOGITS
     \]
    0.60
    ised
    0.54
     Abgerufen
    0.51
     legales
    0.50
     jum
    0.49
     زاده
    0.49
     lah
    0.49
     resten
    0.49
    Purchase
    0.48
    ışı
    0.48
    Activations Density 12.466%

    No Known Activations