© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4939
    Prev
    Next
    INDEX
    Explanations

    legal fine print and campaign donation requests

    oai_token-act-pair · gemini-2.0-flash

    payment

    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
    Negative Logits
    NUMX
    -0.54
    InStock
    -0.48
     trig
    -0.48
    piram
    -0.45
    LOYEES
    -0.45
     MongoClient
    -0.45
    vistar
    -0.45
    Lesson
    -0.45
     LESSON
    -0.45
    źni
    -0.44
    POSITIVE LOGITS
    findpost
    0.68
     legible
    0.68
    Personendaten
    0.63
    GraphicsUnit
    0.61
     handwriting
    0.60
     nakalista
    0.60
     signatory
    0.59
     Италијани
    0.58
    mbggenerated
    0.57
     Walkover
    0.57
    Activations Density 2.743%

    No Known Activations