© 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. 12869
    Prev
    Next
    INDEX
    Explanations

    various characters, letters inside brackets and numbers, possibly related to extracting specific information from code or legal documents

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign 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_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
    emploi
    -0.31
    égalité
    -0.27
    extérieur
    -0.27
     systém
    -0.26
    ীর
    -0.25
    CoV
    -0.25
     náz
    -0.23
     tierra
    -0.23
     grig
    -0.23
     década
    -0.20
    POSITIVE LOGITS
     متعلقه
    1.01
    cotch
    0.96
    upported
    0.94
    yntaxException
    0.93
     GenerationType
    0.93
     betweenstory
    0.91
     المعيارى
    0.90
     Мексичка
    0.90
    hould
    0.90
    afety
    0.90
    Activations Density 30.444%

    No Known Activations