© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4437
    Prev
    Next
    INDEX
    Explanations

    the adjective "smooth", sometimes in conjunction with another physics, engineering, or technical term

    oai_token-act-pair · gemini-2.0-flash

    smooth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Cæsar
    -0.83
     يتيمه
    -0.82
     Jefus
    -0.80
     Púb
    -0.78
     himſelf
    -0.78
     poffe
    -0.76
     itſelf
    -0.76
     armées
    -0.75
     purpoſe
    -0.75
     ſtate
    -0.75
    POSITIVE LOGITS
    ness
    0.72
    s
    0.60
    smarty
    0.58
     Bande
    0.57
    DataManager
    0.57
    :"-"`
    0.57
     <=>
    0.56
    PerformLayout
    0.55
    　　“
    0.55
     kring
    0.54
    Activations Density 2.069%

    No Known Activations