© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10219
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers and website formatting code

    oai_token-act-pair · gemini-2.0-flash

    code/data files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Diwedd
    -0.55
    észetes
    -0.53
     CreateTagHelper
    -0.50
    цездатний
    -0.49
    anément
    -0.48
    ":[{
    -0.47
    InvalidProtocol
    -0.46
     rhestr
    -0.46
    Semoga
    -0.46
     Roskov
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.90
     EconPapers
    0.63
    WriteTagHelper
    0.59
    detectChanges
    0.54
    didSet
    0.54
     GenerationType
    0.52
     useParams
    0.52
    ņš
    0.49
    jfree
    0.49
    OrBuilder
    0.49
    Activations Density 1.566%

    No Known Activations