© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6089
    Prev
    Next
    INDEX
    Explanations

    contexts about crime and being victimized

    oai_token-act-pair · gemini-2.0-flash

    demands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     included
    -0.84
     Includes
    -0.81
     include
    -0.79
     includes
    -0.79
     Included
    -0.78
    Included
    -0.75
    included
    -0.75
     Include
    -0.73
    Includes
    -0.73
     INCLUDE
    -0.73
    POSITIVE LOGITS
     demands
    1.03
     demand
    1.03
     demanding
    0.97
     demanded
    0.96
    demand
    0.94
     Demands
    0.92
     exige
    0.92
     Demand
    0.92
     DEMAND
    0.91
     exigir
    0.90
    Activations Density 0.895%

    No Known Activations