© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15684
    Prev
    Next
    INDEX
    Explanations

    Japanese Java error messages

    oai_token-act-pair · gemini-2.0-flash

    Computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     their
    -0.62
    <eos>
    -0.57
     the
    -0.52
     also
    -0.52
     and
    -0.50
     two
    -0.48
     per
    -0.47
     similar
    -0.47
     your
    -0.47
    l
    -0.46
    POSITIVE LOGITS
     feroit
    1.00
     auroit
    0.97
     étoit
    0.94
     avoient
    0.93
    出版年
    0.90
     myſelf
    0.90
    parsedMessage
    0.90
     ainfi
    0.89
     Forumite
    0.88
     étoient
    0.85
    Activations Density 2.199%

    No Known Activations