© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4130
    Prev
    Next
    INDEX
    Explanations

    words related to Samsung tablet specifications and news

    oai_token-act-pair · gemini-2.0-flash

    arena

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ⓧ
    -0.64
    MemoryWarning
    -0.60
    KommentareTeilen
    -0.60
    numerusform
    -0.59
    BeginContext
    -0.56
     setOpen
    -0.56
     NavController
    -0.54
     NgModule
    -0.50
    AnchorStyles
    -0.50
     HomeComponent
    -0.50
    POSITIVE LOGITS
    CodedInputStream
    0.78
     通販
    0.50
     viste
    0.48
    XPATH
    0.48
     Trotsky
    0.47
    ETING
    0.47
    AntiForgeryToken
    0.47
    retten
    0.46
    /@
    0.46
     Reverso
    0.46
    Activations Density 0.709%

    No Known Activations