© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11992
    Prev
    Next
    INDEX
    Explanations

    words strongly related to exceptions in code

    oai_token-act-pair · gemini-2.0-flash

    Exception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    otide
    -0.54
    -
    -0.53
    DOUBLE
    -0.50
    XmlAccessType
    -0.49
     Bain
    -0.49
    abou
    -0.49
    niques
    -0.47
     nahilalakip
    -0.47
     Tiga
    -0.47
    amis
    -0.46
    POSITIVE LOGITS
    UpInside
    0.56
    Jeografia
    0.51
    €)
    0.51
    serviceWorker
    0.51
     Lordships
    0.49
     €)
    0.49
     poffible
    0.48
    anyeol
    0.48
     poffe
    0.47
     raiſ
    0.47
    Activations Density 1.313%

    No Known Activations