© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8315
    Prev
    Next
    INDEX
    Explanations

    the word 'fortune' or variations thereof

    oai_token-act-pair · gemini-2.0-flash

    Fort locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    primitives
    -0.46
     ma
    -0.39
    antía
    -0.37
     Warenkorb
    -0.36
     premi
    -0.36
    THM
    -0.36
     betweenstory
    -0.35
    Einzelnachweise
    -0.35
      
    -0.35
    IPAC
    -0.35
    POSITIVE LOGITS
    AddHtmlAttribute
    0.66
     CreateTagHelper
    0.63
    TagHelper
    0.61
    +:+
    0.60
    toHaveBeenCalled
    0.60
     Egli
    0.59
     '>=
    0.59
     وتسجيلات
    0.59
     Italij
    0.59
     plais
    0.59
    Activations Density 0.433%

    No Known Activations