© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 94
    Prev
    Next
    INDEX
    Explanations

    one set of texts relating to image selection and another relating to real estate and subscription services

    oai_token-act-pair · gemini-2.0-flash

    confirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ,
    -0.45
     d
    -0.45
     track
    -0.41
    Upload
    -0.41
     statement
    -0.40
     stand
    -0.40
     (
    -0.40
     gates
    -0.40
    statement
    -0.39
     stood
    -0.38
    POSITIVE LOGITS
     يتيمه
    0.98
    XmlAccessorType
    0.81
     transférez
    0.80
    MemoryWarning
    0.78
    MENAFN
    0.77
    GEBURTSDATUM
    0.77
    Personendaten
    0.77
    GraphicsUnit
    0.75
     تضيفلها
    0.75
     незавершена
    0.75
    Activations Density 0.501%

    No Known Activations