© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6652
    Prev
    Next
    INDEX
    Explanations

    words in Croatian related to Facebook accounts, SMS messages, and user agreements

    oai_token-act-pair · gemini-2.0-flash

    za

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     за
    -1.87
    За
    -1.30
     za
    -1.26
     За
    -1.10
    за
    -1.09
     ЗА
    -1.05
    <bos>
    -0.97
    Za
    -0.95
    ЗА
    -0.81
    za
    -0.79
    POSITIVE LOGITS
    setVerticalGroup
    0.64
    WriteTagHelper
    0.62
     EconPapers
    0.59
    CompleteListener
    0.59
     AssemblyCulture
    0.57
    argout
    0.56
    ImageContext
    0.56
     consciences
    0.55
    MemoryWarning
    0.55
    drain
    0.55
    Activations Density 0.797%

    No Known Activations