© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1917
    Prev
    Next
    INDEX
    Explanations

    the word "dead" or "deadlock" or variations of it

    oai_token-act-pair · gemini-2.0-flash

    references to "dead"

    np_token-act-pair-logits · gpt-4o-mini

    dead

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    initComponents
    -0.88
     ProtoMessage
    -0.66
     defaultstate
    -0.65
     wikipagina
    -0.65
    بوابة
    -0.64
    IUrlHelper
    -0.59
    AndEndTag
    -0.58
     kasarigan
    -0.57
    Personendaten
    -0.57
    Portail
    -0.56
    POSITIVE LOGITS
     serious
    0.65
    liez
    0.61
     cation
    0.59
    cios
    0.57
     fourth
    0.56
    lifts
    0.55
    iotensin
    0.54
    prez
    0.54
    Stap
    0.54
     Serious
    0.54
    Activations Density 0.812%

    No Known Activations