© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13033
    Prev
    Next
    INDEX
    Explanations

    the word "door"

    oai_token-act-pair · gemini-2.0-flash

    door

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     door
    -2.91
    door
    -2.47
     Door
    -2.36
    Door
    -2.31
     DOOR
    -2.11
     doors
    -1.99
    DOOR
    -1.75
    doors
    -1.63
     Doors
    -1.55
     puerta
    -1.45
    POSITIVE LOGITS
     CreateTagHelper
    1.06
     resourceCulture
    1.01
     typelib
    0.96
     autorytatywna
    0.90
     protoimpl
    0.90
    ImageContext
    0.89
     '\\;'
    0.86
     CHtml
    0.85
    تقاوى
    0.85
    contentLoaded
    0.84
    Activations Density 0.236%

    No Known Activations