© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 847
    Prev
    Next
    INDEX
    Explanations

    words related to modification, endings in 'ing', or those related to math

    oai_token-act-pair · gemini-2.0-flash

    ing endings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    izing
    -0.76
     taking
    -0.69
    ating
    -0.69
     selecting
    -0.69
    riding
    -0.67
    ising
    -0.65
     analyzing
    -0.65
     creating
    -0.64
     applying
    -0.64
    creating
    -0.63
    POSITIVE LOGITS
    ⟬
    0.71
    Geplaatst
    0.69
    edicated
    0.67
    moteur
    0.66
     Administrativna
    0.65
    पया
    0.64
     vectorielles
    0.64
     asupra
    0.63
    ثيق
    0.63
     prosecute
    0.63
    Activations Density 10.932%

    No Known Activations