© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14117
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming documentation that might include HTML, XML, or other code-related tags and syntax

    oai_token-act-pair · gemini-2.0-flash

    HTML 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ↵
    -0.81
     D
    -0.76
     R
    -0.69
     K
    -0.69
     P
    -0.69
     C
    -0.68
     L
    -0.68
    <eos>
    -0.67
     B
    -0.66
     G
    -0.65
    POSITIVE LOGITS
     Monfieur
    1.13
     doubtnut
    1.13
     auffi
    1.08
     Theſe
    1.08
    IntoConstraints
    1.05
     itſelf
    1.05
     ―――――
    1.05
     Jefus
    1.03
     myſelf
    1.02
     Anſ
    0.99
    Activations Density 7.753%

    No Known Activations