© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2521
    Prev
    Next
    INDEX
    Explanations

    the names of research journals, funding sources, publication ethics policies, and links and identifiers associated with academic publications

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    usercontent
    -0.56
     "..\..\
    -0.51
     gọn
    -0.46
     "..\..\..\
    -0.40
    EDEFAULT
    -0.40
    Begriffsklä
    -0.39
     Performing
    -0.39
    şem
    -0.38
     deta
    -0.38
    inguishing
    -0.38
    POSITIVE LOGITS
    SharedCtor
    0.69
    Portail
    0.67
     comunale
    0.63
     resourceCulture
    0.61
    čem
    0.60
     Monfieur
    0.59
    tagext
    0.59
    skap
    0.58
    cipline
    0.58
    verifyException
    0.58
    Activations Density 0.572%

    No Known Activations