© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1734
    Prev
    Next
    INDEX
    Explanations

    a mix of Russian/Slavic language related to programming or system errors, or translation of "Hello"

    oai_token-act-pair · gemini-2.0-flash

    code snippets and messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    \{\\
    -0.62
    ่านั้น
    -0.60
     sih
    -0.58
    εται
    -0.56
    uthorized
    -0.54
     Biro
    -0.52
     sini
    -0.52
    eated
    -0.50
    uesday
    -0.50
    λων
    -0.50
    POSITIVE LOGITS
    .
    0.64
    contentLoaded
    0.61
    elemField
    0.56
     reflectivity
    0.56
     breasted
    0.50
    XMLSchema
    0.50
    ])){
    0.50
     flexível
    0.49
     samfun
    0.48
    itteet
    0.48
    Activations Density 3.000%

    No Known Activations