© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5634
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing' or 'ed' that imply importance or consequence

    oai_token-act-pair · gemini-2.0-flash

    happening

    np_max-act · 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
    ousands
    -0.70
    hematical
    -0.69
    AlterField
    -0.68
     tetanus
    -0.68
    :+:
    -0.66
    ientôt
    -0.65
    ricultural
    -0.63
    UBLIC
    -0.61
     Houſe
    -0.61
    DispatchToProps
    -0.61
    POSITIVE LOGITS
    <bos>
    2.27
     the
    0.62
    '
    0.56
    D
    0.54
    T
    0.54
    B
    0.53
    L
    0.49
    -
    0.49
    R
    0.49
    H
    0.48
    Activations Density 1.983%

    No Known Activations