© 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. 13138
    Prev
    Next
    INDEX
    Explanations

    the word "pull" and related words like "towed".

    oai_token-act-pair · gemini-2.0-flash

    pull

    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
     pull
    -2.97
    pull
    -2.77
     Pull
    -2.67
     pulls
    -2.63
     pulling
    -2.61
     pulled
    -2.61
    Pull
    -2.56
     PULL
    -2.41
     Pulling
    -2.33
    pulled
    -2.19
    POSITIVE LOGITS
    .*")]
    0.66
    ]]
    0.57
     iprot
    0.55
     eût
    0.53
    hauses
    0.52
     avoient
    0.52
     BoxDecoration
    0.51
    ürtel
    0.51
     JPanel
    0.51
    \"");
    0.51
    Activations Density 0.774%

    No Known Activations