© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8360
    Prev
    Next
    INDEX
    Explanations

    text relating to a person's career, specifically their retirement and dates

    oai_token-act-pair · gemini-2.0-flash

    retire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    rinfo
    -0.58
    Autoritní
    -0.52
    terscotch
    -0.50
    jboss
    -0.47
     dureza
    -0.45
     Meier
    -0.45
     fondamentali
    -0.44
     achtergrond
    -0.44
    yntaxException
    -0.44
     vriend
    -0.43
    POSITIVE LOGITS
    oneofs
    0.70
     typelib
    0.64
     насељу
    0.56
    basicConfig
    0.56
    ::_('
    0.54
    jsxFileName
    0.52
    DockStyle
    0.52
    WriteBarrier
    0.51
    WithMany
    0.50
    GIVEREF
    0.50
    Activations Density 0.175%

    No Known Activations