© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2551
    Prev
    Next
    INDEX
    Explanations

    mentions of studies, results, and future implications, especially in scientific studies.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     the
    -0.59
    tagHelperRunner
    -0.59
    UnusedPrivate
    -0.57
    󠁢
    -0.56
    NOPQRST
    -0.54
     piattaforma
    -0.53
     BorderSide
    -0.52
     estekak
    -0.52
    rungsseite
    -0.50
     lendemain
    -0.50
    POSITIVE LOGITS
    Архівовано
    0.68
     degree
    0.61
     overall
    0.59
     quality
    0.55
     single
    0.54
     means
    0.54
     arrangement
    0.53
    راتيج
    0.53
     extent
    0.53
    overall
    0.53
    Activations Density 3.213%

    No Known Activations