© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2884
    Prev
    Next
    INDEX
    Explanations

    excerpts about software, hardware, applications, patches and/or updates

    oai_token-act-pair · gemini-2.0-flash

    mentions of tech companies and platforms

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

    social media platforms

    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
    basicConfig
    -0.52
     NUKAT
    -0.50
    صرية
    -0.50
    Grüsse
    -0.49
     Mitteln
    -0.48
    êle
    -0.48
    ]]]
    -0.47
    asticity
    -0.47
    Geplaatst
    -0.45
    SystemColors
    -0.45
    POSITIVE LOGITS
     Google
    0.82
     CreateTagHelper
    0.74
     iOS
    0.70
     Facebook
    0.69
     Instagram
    0.68
     WhatsApp
    0.67
     Spotify
    0.67
    Google
    0.66
     GOOGLE
    0.66
     google
    0.65
    Activations Density 12.068%

    No Known Activations