© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13813
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe how something is surprising, alarming, sad or otherwise sensational

    oai_token-act-pair · gemini-2.0-flash

    development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     الاطلاع
    -0.51
    ador
    -0.49
    principalTable
    -0.48
    воря
    -0.47
    AddTagHelper
    -0.46
    RunAsync
    -0.46
    abestanden
    -0.46
    jsdelivr
    -0.46
     perceber
    -0.45
    ATURE
    -0.44
    POSITIVE LOGITS
     development
    1.90
     Development
    1.69
    development
    1.62
    Development
    1.60
     DEVELOPMENT
    1.59
    DEVELOPMENT
    1.29
     desarrollo
    1.24
     développement
    1.19
     desenvolvimento
    1.15
     Entwicklung
    1.11
    Activations Density 4.398%

    No Known Activations