© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12499
    Prev
    Next
    INDEX
    Explanations

    time zones and related words

    oai_token-act-pair · gemini-2.0-flash

    say zone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     zone
    -1.99
     Zone
    -1.98
    Zone
    -1.92
     ZONE
    -1.84
     Zones
    -1.81
     zones
    -1.76
    zone
    -1.74
     territory
    -1.68
    ZONE
    -1.66
    Zones
    -1.59
    POSITIVE LOGITS
    abestanden
    0.70
     bezeichneter
    0.52
    utives
    0.49
     gyhoeddwyd
    0.48
     "..\..\..\
    0.48
     "..\..\
    0.46
    ("*");
    0.46
    red
    0.45
    참고
    0.45
    ర్య
    0.44
    Activations Density 1.977%

    No Known Activations