© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6318
    Prev
    Next
    INDEX
    Explanations

    the word "launched" indicating the start of something, and words related to results

    oai_token-act-pair · gemini-2.0-flash

    launched

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.21
     itſelf
    -0.96
     myſelf
    -0.81
    ^(@)
    -0.80
     raiſ
    -0.80
     ―――――
    -0.77
    Fordítás
    -0.76
     whoſe
    -0.75
     ſind
    -0.74
    vedades
    -0.73
    POSITIVE LOGITS
     BrowserModule
    0.67
    Rüyada
    0.65
    esModule
    0.55
    ligo
    0.54
    BrowserModule
    0.54
     mathematically
    0.54
     Harwood
    0.53
     
    0.53
    organisation
    0.52
    ingi
    0.52
    Activations Density 3.205%

    No Known Activations