© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1569
    Prev
    Next
    INDEX
    Explanations

    words related to walking and paths

    oai_token-act-pair · gemini-2.0-flash

    walking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     walking
    -0.96
     walk
    -0.90
     Walk
    -0.88
     Walking
    -0.85
    walking
    -0.82
    Walking
    -0.81
     walked
    -0.81
     WALK
    -0.80
    Walk
    -0.76
    walk
    -0.71
    POSITIVE LOGITS
    <bos>
    0.83
    ThroughAttribute
    0.75
     zelve
    0.66
     itſelf
    0.66
     Shakspeare
    0.62
     surla
    0.61
     näh
    0.60
     againſt
    0.60
    FTFY
    0.60
     curtain
    0.60
    Activations Density 12.248%

    No Known Activations