© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11458
    Prev
    Next
    INDEX
    Explanations

    promotional offers for insurance customers

    oai_token-act-pair · gemini-2.0-flash

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     AssemblyProduct
    -0.70
    InjectAttribute
    -0.63
    ']))
    -0.63
     cherchés
    -0.60
    AutoField
    -0.59
     Administrativna
    -0.59
    GraphicsUnit
    -0.56
    namefont
    -0.56
    "):
    -0.56
    yntaxException
    -0.56
    POSITIVE LOGITS
    PMailer
    0.45
    XmlAccessorType
    0.45
     tận
    0.45
    PHPExcel
    0.44
    CAPTURE
    0.44
     يتيمه
    0.43
    Aprove
    0.43
    jws
    0.43
    Abitanti
    0.43
    erenc
    0.43
    Activations Density 0.246%

    No Known Activations