© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6530
    Prev
    Next
    INDEX
    Explanations

    URLs for, references to, or mentions of Facebook pages

    oai_token-act-pair · gemini-2.0-flash

    Facebook-related content

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

    facebook

    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
     Roskov
    -1.09
    yntaxException
    -0.88
    tvguidetime
    -0.83
    ſelf
    -0.82
     betweenstory
    -0.82
     تضيفلها
    -0.82
     itſelf
    -0.79
    parsedMessage
    -0.77
    AndEndTag
    -0.77
    angliski
    -0.75
    POSITIVE LOGITS
     d
    0.57
     tra
    0.50
     mo
    0.47
     Go
    0.44
    chw
    0.44
    ře
    0.44
     dis
    0.43
     unter
    0.42
     mer
    0.42
     s
    0.41
    Activations Density 0.775%

    No Known Activations