© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7820
    Prev
    Next
    INDEX
    Explanations

    angle brackets and curly braces, common in HTML, XML, and code

    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_18/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.18.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
     BorderSide
    -0.77
    ThroughAttribute
    -0.75
     purpoſe
    -0.73
    PerformLayout
    -0.71
    RetentionPolicy
    -0.70
     contextLoads
    -0.69
     sauvages
    -0.68
     snippetHide
    -0.64
     humaines
    -0.63
     laſt
    -0.62
    POSITIVE LOGITS
    <bos>
    0.60
     colspan
    0.47
    ModelAndView
    0.47
    haw
    0.45
     deal
    0.43
    viso
    0.43
    </tr>
    0.43
    ểm
    0.43
    Content
    0.42
    angani
    0.42
    Activations Density 0.010%

    No Known Activations