© 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. 7529
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with academic publishing

    oai_token-act-pair · gemini-2.0-flash

    words related to research and description

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

    publications

    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
    MigrationBuilder
    -0.55
     estimés
    -0.51
    lause
    -0.45
    ©
    -0.43
     ơn
    -0.41
    Hear
    -0.41
    裔
    -0.41
    ariously
    -0.40
     nonatomic
    -0.40
    ското
    -0.40
    POSITIVE LOGITS
     about
    1.13
     describing
    0.96
    about
    0.94
    describing
    0.91
     discussing
    0.91
     describe
    0.88
     tentang
    0.84
     ABOUT
    0.82
     discuss
    0.82
     description
    0.81
    Activations Density 3.080%

    No Known Activations