© 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. 3282
    Prev
    Next
    INDEX
    Explanations

    words indicating measurement, quantity, or degree

    oai_token-act-pair · gemini-2.0-flash

    specification of a subset

    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
     debt
    -0.56
     agreement
    -0.56
    walde
    -0.56
    łku
    -0.52
     оригіналу
    -0.52
    Hockey
    -0.50
     eaten
    -0.49
     Avic
    -0.49
     Rockland
    -0.49
     reti
    -0.48
    POSITIVE LOGITS
     Normdatei
    0.71
     nahilalakip
    0.68
     createState
    0.66
    __':
    0.63
    μβρίου
    0.61
    ￡
    0.59
    tvguidetime
    0.57
    :✨
    0.57
     يتيمه
    0.57
    CloseOperation
    0.57
    Activations Density 4.379%

    No Known Activations