© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14327
    Prev
    Next
    INDEX
    Explanations

    situations in which someone has been taken somewhere against their will

    oai_token-act-pair · gemini-2.0-flash

    someone removed

    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
     autorytatywna
    -0.88
    TagHelper
    -0.66
    Quiénes
    -0.59
     JsonConvert
    -0.57
     ioutil
    -0.57
     مشارکت‌کنندگان
    -0.56
    Referencies
    -0.56
     aDecoder
    -0.55
     modelAndView
    -0.54
    TagMode
    -0.53
    POSITIVE LOGITS
    RTEE
    0.52
    bitField
    0.51
     GeoNames
    0.51
     Roskov
    0.49
     entourage
    0.44
    featureID
    0.43
     تعدى
    0.43
     famí
    0.43
    rrggbb
    0.43
     OFDb
    0.42
    Activations Density 2.510%

    No Known Activations