© 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. 11649
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to art, performance, or literature within the context of reviews, descriptions or commentary

    oai_token-act-pair · 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
    BuilderFactory
    -0.54
     Weyl
    -0.52
     FileWriter
    -0.52
    multer
    -0.52
    ンテージ
    -0.50
    psia
    -0.49
    antaine
    -0.49
     Churchill
    -0.48
     angiography
    -0.48
    Cubit
    -0.48
    POSITIVE LOGITS
     وتسجيلات
    0.64
     onPostExecute
    0.61
     bar
    0.55
    EDEFAULT
    0.53
     Bar
    0.53
    IBar
    0.49
    XMLSchema
    0.49
     opérateur
    0.48
    الإنجليزية
    0.48
     romantic
    0.48
    Activations Density 1.069%

    No Known Activations