© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12258
    Prev
    Next
    INDEX
    Explanations

    negative statements about public infrastructure, and religious festivals in India, especially Diwali

    oai_token-act-pair · gemini-2.0-flash

    Describing locations

    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
    GEBURTSDATUM
    -0.75
     AspNetCore
    -0.74
    DeleteBehavior
    -0.65
    RegisterType
    -0.61
    Бележки
    -0.60
    TagMode
    -0.60
    Дереккөздер
    -0.60
    ConstraintMaker
    -0.60
     Roskov
    -0.58
    mybatisplus
    -0.57
    POSITIVE LOGITS
     near
    0.66
    }{*}{
    0.57
    near
    0.52
     محفوظة
    0.48
     snippetHide
    0.46
     daw
    0.44
    Near
    0.43
     Near
    0.43
    acrylate
    0.41
    onActivityResult
    0.41
    Activations Density 4.163%

    No Known Activations