© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4501
    Prev
    Next
    INDEX
    Explanations

    a mix of Spanish and programming-related words.

    oai_token-act-pair · gemini-2.0-flash

    Multiple languagesMethod: 4Reason: The texts contain snippets of multiple languages, including Spanish, French, and Italian.Multiple languages

    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
     Real
    -0.48
    TableAdapter
    -0.48
     real
    -0.47
    Real
    -0.43
    esen
    -0.41
     Red
    -0.41
    lf
    -0.40
    reeg
    -0.40
     LoggerFactory
    -0.39
    sphin
    -0.39
    POSITIVE LOGITS
     betweenstory
    0.81
    rawDesc
    0.68
     Italijanski
    0.68
     विश्वसनीयता
    0.67
    msgTypes
    0.64
    πάρχ
    0.63
     FetchType
    0.63
     HttpNotFound
    0.63
    ArrowToggle
    0.63
     conmigo
    0.61
    Activations Density 0.732%

    No Known Activations