© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3651
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to what someone would do or likely do

    oai_token-act-pair · gemini-2.0-flash

    Expressing hypothetical scenarios

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     myſelf
    -0.92
     Theſe
    -0.83
     raiſ
    -0.81
     itſelf
    -0.80
     ſtate
    -0.79
     ſeveral
    -0.77
    ſelf
    -0.76
     uſe
    -0.75
     purpoſe
    -0.75
     themſelves
    -0.74
    POSITIVE LOGITS
     first
    0.50
     notice
    0.44
    发现
    0.43
     Baillargeon
    0.42
     primeros
    0.42
     vz
    0.41
     revel
    0.41
     complete
    0.41
    ↵
    0.41
    ia
    0.41
    Activations Density 1.187%

    No Known Activations