© 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. 6960
    Prev
    Next
    INDEX
    Explanations

    Java-related error messages, particularly those related to class initialization

    oai_token-act-pair · gemini-2.0-flash

    Engineering, manufacturing, science

    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
     $_"
    -0.79
     Theſe
    -0.77
     bezeichneter
    -0.76
    ſelf
    -0.76
    OGND
    -0.73
     NDEBUG
    -0.73
     CHAPITRE
    -0.71
     TOKYO
    -0.69
     Efq
    -0.68
     Мексичка
    -0.67
    POSITIVE LOGITS
     trono
    0.37
     jarak
    0.35
    práv
    0.33
    جابة
    0.33
     pandangan
    0.33
     szeret
    0.32
     apoder
    0.31
     sveta
    0.30
    百分
    0.29
     floresta
    0.29
    Activations Density 7.038%

    No Known Activations