© 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. 12197
    Prev
    Next
    INDEX
    Explanations

    snippets of code in a variety of programming languages

    oai_token-act-pair · gemini-2.0-flash

    words with archaic or stylized spellings

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

    code

    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
     et
    -0.98
     I
    -0.93
     N
    -0.90
     J
    -0.89
     de
    -0.88
     K
    -0.87
     e
    -0.86
     mit
    -0.85
     U
    -0.85
     M
    -0.84
    POSITIVE LOGITS
     itſelf
    1.86
     myſelf
    1.81
     pleaſure
    1.66
     Monfieur
    1.62
     greateſt
    1.61
     Reſ
    1.59
     Jefus
    1.59
     Majefty
    1.59
     ſeveral
    1.55
     purpoſe
    1.55
    Activations Density 4.037%

    No Known Activations