© 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. 6316
    Prev
    Next
    INDEX
    Explanations

    the word "various" and "body" and "parts" and numbers and modifiers like "several"

    oai_token-act-pair · gemini-2.0-flash

    various

    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
     various
    -1.66
    various
    -1.43
    Various
    -1.20
     Various
    -1.15
    各种
    -0.98
    各種
    -0.95
     VARIOUS
    -0.94
     berbagai
    -0.85
     variously
    -0.75
     diversos
    -0.75
    POSITIVE LOGITS
    Portail
    0.87
    findpost
    0.83
    httphttps
    0.82
     Roskov
    0.81
    WebVitals
    0.81
    bewerken
    0.78
    Kaieteur
    0.77
    HomeAsUpEnabled
    0.76
    ManagedBean
    0.75
    GraphicsUnit
    0.74
    Activations Density 3.152%

    No Known Activations