© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4018
    Prev
    Next
    INDEX
    Explanations

    the word "tackle" and also the word "grid", with a very weak activation on the definite article "the"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    eeeeee
    -0.64
     Uni
    -0.64
     dro
    -0.63
    alised
    -0.62
    atemala
    -0.60
    춰
    -0.57
     inc
    -0.57
     volume
    -0.56
     pre
    -0.56
     structure
    -0.56
    POSITIVE LOGITS
     zijne
    1.06
     supérieurs
    0.97
     feroit
    0.92
     suivants
    0.88
     démocr
    0.88
     figliu
    0.88
     normaux
    0.87
     généraux
    0.87
     auroit
    0.86
     enfans
    0.85
    Activations Density 2.176%

    No Known Activations