© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9386
    Prev
    Next
    INDEX
    Explanations

    the word "provider."

    oai_token-act-pair · gemini-2.0-flash

    provider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     LoginComponent
    -0.60
    pygame
    -0.60
    WaitGroup
    -0.60
    (‘
    -0.57
     årene
    -0.56
    Rüyada
    -0.56
    plz
    -0.55
     plz
    -0.55
     Kindly
    -0.54
    IBOutlet
    -0.53
    POSITIVE LOGITS
    раздо
    0.85
    достатки
    0.69
    canestro
    0.65
     SIMBAD
    0.64
    yaszt
    0.62
    Malley
    0.61
     glaubte
    0.61
     wading
    0.59
    jména
    0.59
     ujednoznacz
    0.58
    Activations Density 0.518%

    No Known Activations