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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5614
    Prev
    Next
    INDEX
    Explanations

    words associated with community amenities like parks, pools, and clubhouses.

    oai_token-act-pair · gemini-2.0-flash

    features of community facilities

    np_token-act-pair-logits · gpt-4o-mini

    Locations and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Theſe
    -0.94
     poffible
    -0.94
     Majefty
    -0.92
     Jefus
    -0.91
     itſelf
    -0.90
     houſe
    -0.88
     reaſon
    -0.88
     Efq
    -0.87
     myſelf
    -0.87
     ſeveral
    -0.85
    POSITIVE LOGITS
     
    0.54
     V
    0.50
     "
    0.50
     multi
    0.49
     children
    0.49
    <eos>
    0.48
     i
    0.47
     J
    0.46
     As
    0.46
     X
    0.46
    Activations Density 0.598%

    No Known Activations