© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16204
    Prev
    Next
    INDEX
    Explanations

    words related to walking

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Geplaatst
    -0.66
    ReusableCell
    -0.62
    <bos>
    -0.56
     referenties
    -0.54
    Jereo
    -0.54
     læng
    -0.52
    __*/
    -0.50
    Източници
    -0.49
     flesta
    -0.48
    Šaltiniai
    -0.47
    POSITIVE LOGITS
     walks
    0.84
     walkers
    0.82
     walking
    0.81
     walk
    0.80
    walks
    0.78
     walked
    0.74
    walk
    0.73
    Walk
    0.72
     walkways
    0.68
     Walking
    0.68
    Activations Density 0.793%

    No Known Activations