© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13153
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BeginContext
    -0.90
    (
    -0.81
    LookAnd
    -0.79
    "
    -0.78
     pinulongan
    -0.75
    jsxFileName
    -0.72
     NUKAT
    -0.70
    tagHelperRunner
    -0.69
    RegistryLite
    -0.69
     متعلقه
    -0.67
    POSITIVE LOGITS
     kvinna
    0.57
     död
    0.54
     naturais
    0.51
     vastaan
    0.51
     verksamhet
    0.50
     bidra
    0.50
     bēr
    0.50
     varandra
    0.49
     kautta
    0.49
     säll
    0.49
    Activations Density 2.726%

    No Known Activations