© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13678
    Prev
    Next
    INDEX
    Explanations

    phrases representing strongly-held traditional ideas

    oai_token-act-pair · gemini-2.0-flash

    Ideas and beliefs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     estekak
    -0.65
    ########.
    -0.65
    
    -0.63
    หวัด
    -0.61
    脚注の使い方
    -0.57
    ughter
    -0.55
     AssemblyTitle
    -0.53
    ResponseWriter
    -0.53
     pageContext
    -0.52
    لينكات
    -0.52
    POSITIVE LOGITS
     caractéristique
    0.55
     CHU
    0.54
     Pandit
    0.53
    GraphicsUnit
    0.53
     iStock
    0.53
    我一直
    0.52
    AutoSize
    0.52
    imentel
    0.52
    Kilder
    0.51
    demy
    0.50
    Activations Density 1.661%

    No Known Activations