© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7431
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on continuations, whether in medicine, rally driving, code, or life in general.

    oai_token-act-pair · gemini-2.0-flash

    Sentence continuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     continuing
    -2.94
     continue
    -2.92
    continue
    -2.91
     continued
    -2.86
     continues
    -2.80
     Continue
    -2.66
    continued
    -2.63
    continuing
    -2.63
     Continuing
    -2.63
    Continuing
    -2.58
    POSITIVE LOGITS
    marle
    0.56
    prefixer
    0.48
    iastes
    0.47
    attet
    0.47
    itta
    0.47
    itten
    0.47
    ROZ
    0.46
    fection
    0.45
    kosh
    0.45
    orcid
    0.45
    Activations Density 2.822%

    No Known Activations