© 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. 2294
    Prev
    Next
    INDEX
    Explanations

    code and code-like text with formatting and comments

    oai_token-act-pair · gemini-2.0-flash

    words with unusual characters or archaic spellings

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

    Code contexts

    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
     M
    -0.62
    ⎨
    -0.60
    ↵
    -0.57
    <eos>
    -0.56
     A
    -0.56
    ValueStyle
    -0.55
     I
    -0.52
     f
    -0.50
    posten
    -0.50
     i
    -0.50
    POSITIVE LOGITS
     Efq
    1.00
     Monfieur
    0.93
     pleaſure
    0.88
     Majefty
    0.87
     Theſe
    0.87
     becauſe
    0.86
     myſelf
    0.85
     greateſt
    0.85
     whoſe
    0.82
     Reſ
    0.82
    Activations Density 1.228%

    No Known Activations