© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12541
    Prev
    Next
    INDEX
    Explanations

    program code and finance/radio related words

    oai_token-act-pair · gemini-2.0-flash

    forward movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     advance
    -1.55
    Advance
    -1.55
     Advance
    -1.48
    advance
    -1.45
     advances
    -1.34
     advanced
    -1.27
     avancée
    -1.27
    advanced
    -1.25
     advancement
    -1.20
     progress
    -1.20
    POSITIVE LOGITS
    NameInMap
    0.60
    rogenic
    0.57
     Evita
    0.54
     CreateTagHelper
    0.53
    ajur
    0.50
    citep
    0.49
    Архівовано
    0.49
     Attra
    0.49
    saraba
    0.49
     विश्वसनीयता
    0.48
    Activations Density 53.886%

    No Known Activations