© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    tokens associated with scientific and medical research papers

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical vocabulary

    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
     CURIAM
    -0.60
    tanleria
    -0.56
     Vero
    -0.54
     Abu
    -0.54
     nahilalakip
    -0.53
    vician
    -0.52
    Билгалдахарш
    -0.52
    DebuggerNonUser
    -0.52
    bewerken
    -0.51
     Amman
    -0.51
    POSITIVE LOGITS
    ас
    0.71
    acar
    0.66
    ac
    0.64
     GenerationType
    0.64
    acc
    0.63
    acs
    0.63
    aca
    0.62
    acr
    0.61
     ac
    0.61
    acias
    0.58
    Activations Density 4.164%

    No Known Activations