© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13420
    Prev
    Next
    INDEX
    Explanations

    the name "Ros"

    oai_token-act-pair · gemini-2.0-flash

    the name "Rose"

    np_token-act-pair-logits · gpt-4o-mini

    Ros/Rose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Prise
    -0.49
    carpa
    -0.47
     EClass
    -0.45
     consejos
    -0.45
    υμα
    -0.44
    bonucleic
    -0.44
     sleeve
    -0.43
    το
    -0.43
     Endocrine
    -0.43
     altas
    -0.42
    POSITIVE LOGITS
    évaluateur
    0.75
     Italijanski
    0.62
     AssemblyCulture
    0.59
    poel
    0.55
    RTDA
    0.53
    nachron
    0.50
    XmlAccessType
    0.50
     муніципалі
    0.50
     betweenstory
    0.50
    󠁴
    0.50
    Activations Density 0.330%

    No Known Activations