© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16023
    Prev
    Next
    INDEX
    Explanations

    words related to locations, maps, or journeys, and instructions

    oai_token-act-pair · gemini-2.0-flash

    Bring, take

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    setVerticalGroup
    -0.53
    RRect
    -0.52
    tagext
    -0.52
    intios
    -0.51
    UIControlState
    -0.45
    
    -0.44
     kapp
    -0.44
    lijken
    -0.44
    MenuInflater
    -0.43
    obald
    -0.43
    POSITIVE LOGITS
     take
    1.16
     bring
    1.15
     brought
    1.13
     takes
    1.09
     llevar
    1.09
    带
    1.09
    Brought
    1.07
    take
    1.05
     Bring
    1.05
     membawa
    1.05
    Activations Density 1.513%

    No Known Activations