© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12728
    Prev
    Next
    INDEX
    Explanations

    phone numbers and other numbers followed by colons

    oai_token-act-pair · gemini-2.0-flash

    Phone numbers and numerical codes

    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
     Савезне
    -1.00
    SharedCtor
    -0.98
    addCriterion
    -0.98
     AssemblyCompany
    -0.93
    IsContent
    -0.89
    AddTagHelper
    -0.87
    principalColumn
    -0.84
    Autoritní
    -0.81
    XmlAccessorType
    -0.79
    RUnlock
    -0.78
    POSITIVE LOGITS
     "
    0.40
     tessuto
    0.40
     esportivo
    0.37
     hlavy
    0.36
    لاح
    0.36
     orgánico
    0.36
     srdce
    0.35
     morrer
    0.35
     ufficiali
    0.35
     or
    0.35
    Activations Density 1.884%

    No Known Activations