© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14180
    Prev
    Next
    INDEX
    Explanations

    abbreviations and short versions of words, especially in technical or scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    say "ers" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ftagPool
    -0.62
    indak
    -0.60
    ILayout
    -0.60
     (;;
    -0.56
    Rhestr
    -0.56
     useDispatch
    -0.55
    SwingConstants
    -0.55
    strando
    -0.54
    protoc
    -0.54
    jspx
    -0.53
    POSITIVE LOGITS
    ers
    1.23
    ERS
    1.13
    er
    0.98
    ters
    0.97
    ER
    0.91
    ered
    0.89
    ter
    0.88
    ders
    0.87
     ers
    0.86
    der
    0.85
    Activations Density 6.142%

    No Known Activations