© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, colons, a few verbs, and parenthetical information, making it difficult to describe concisely.

    oai_token-act-pair · gemini-2.0-flash

    pattern of comments or dialogue

    np_token-act-pair-logits · gpt-4o-mini
    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
    DOUT
    -0.46
    RegressionTest
    -0.46
    trage
    -0.42
    iour
    -0.41
     Pantry
    -0.41
     std
    -0.40
     مرئيه
    -0.40
     tap
    -0.40
     Plant
    -0.39
    RequestBuilder
    -0.39
    POSITIVE LOGITS
    KommentareTeilen
    0.81
    DeleteBehavior
    0.79
     متعلقه
    0.77
    StoryboardSegue
    0.73
     initComponents
    0.73
     Мексичка
    0.73
     protoimpl
    0.71
    IUrlHelper
    0.71
     @"/
    0.67
    migrationBuilder
    0.66
    Activations Density 0.391%

    No Known Activations