© 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. 13002
    Prev
    Next
    INDEX
    Explanations

    mentions of events that happened at a specific time in the past

    oai_token-act-pair · gemini-2.0-flash

    dates/time

    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
     Exactos
    -0.58
     HasFactory
    -0.54
     NgModule
    -0.50
    AddHtmlAttribute
    -0.50
    createComponent
    -0.49
    SBATCH
    -0.49
     AssemblyProduct
    -0.48
    DllImport
    -0.47
     NSCoder
    -0.46
    tattoo
    -0.46
    POSITIVE LOGITS
    Życiorys
    0.59
     unknownFields
    0.54
    InitStruct
    0.53
     Frig
    0.53
     متعلقه
    0.53
    DebuggerNonUser
    0.52
     tournée
    0.52
    UnusedPrivate
    0.51
    érieures
    0.51
     بتاريخ
    0.51
    Activations Density 1.463%

    No Known Activations