© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6662
    Prev
    Next
    INDEX
    Explanations

    text discussing phonon-mediated superconductivity and related concepts

    oai_token-act-pair · gemini-2.0-flash

    technical terms in programming or technology

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

    superconductivity

    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
     Paglinawan
    -0.63
    ThroughAttribute
    -0.59
    Xna
    -0.57
    tvguidetime
    -0.56
     فريبيس
    -0.56
    bkz
    -0.56
    helial
    -0.55
    IBarButtonItem
    -0.55
    Filmographie
    -0.55
    脚注の使い方
    -0.54
    POSITIVE LOGITS
    ValueStyle
    0.56
     fractional
    0.49
    mappedBy
    0.45
     jScrollPane
    0.45
     scenario
    0.44
    ImageContext
    0.43
    subpackage
    0.43
    RTEE
    0.43
    putExtra
    0.43
     NSCoder
    0.41
    Activations Density 2.831%

    No Known Activations