© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15526
    Prev
    Next
    INDEX
    Explanations

    scientific research publications and terminology

    oai_token-act-pair · gemini-2.0-flash

    PhysRevLett

    np_max-act · gemini-2.0-flash

    PhysRevLett

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     wireType
    -0.96
    antMatchers
    -0.90
    }{*}{
    -0.88
     EClass
    -0.81
    "',
    -0.80
     للاسماء
    -0.78
    NameInMap
    -0.77
    UrlResolution
    -0.77
    yntaxException
    -0.77
    **/
    -0.75
    POSITIVE LOGITS
     éditoriale
    0.66
     égal
    0.66
     désol
    0.64
    𝐥
    0.64
     McIl
    0.64
     vigne
    0.64
    UALA
    0.64
     Kl
    0.64
     aluguel
    0.63
    datal
    0.63
    Activations Density 19.764%

    No Known Activations