© 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. 9128
    Prev
    Next
    INDEX
    Explanations

    html syntax such as 'div' and 'text'

    oai_token-act-pair · gemini-2.0-flash

    code snippets or components

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

    Code and HTML

    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
    不受
    -0.42
    [/
    -0.41
     réguli
    -0.40
     sammen
    -0.40
    LL
    -0.39
     partagé
    -0.39
     bebas
    -0.37
     affatto
    -0.36
     diventare
    -0.36
    сп
    -0.36
    POSITIVE LOGITS
    +#+#
    0.82
    RegressionTest
    0.81
    newswire
    0.79
    LookAnd
    0.78
     يتيمه
    0.76
     propOrder
    0.74
    contentLoaded
    0.74
    Cyfeiriadau
    0.73
    StoryboardSegue
    0.72
    ItemBackground
    0.71
    Activations Density 0.732%

    No Known Activations