© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 397
    Prev
    Next
    INDEX
    Explanations

    scientific discussion of wood as a material, use, or product.

    oai_token-act-pair · gemini-2.0-flash

    wood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     wood
    -2.25
     Wood
    -2.08
    Wood
    -1.98
     WOOD
    -1.82
    wood
    -1.74
    WOOD
    -1.69
     wooden
    -1.38
    woods
    -1.34
     madera
    -1.34
     woods
    -1.27
    POSITIVE LOGITS
     utafitiHapana
    0.79
     ujednoznacz
    0.75
    ussis
    0.74
    abetes
    0.73
     Administrativna
    0.70
    lorette
    0.68
    Jeografia
    0.67
    mobileqq
    0.66
     >=",
    0.66
    Біографія
    0.65
    Activations Density 6.801%

    No Known Activations