© 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. 10774
    Prev
    Next
    INDEX
    Explanations

    words related to learning and computer file maintenance

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act · gemini-2.0-flash

    plural nouns

    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
     pouvoirs
    -1.96
     églises
    -1.93
     preuves
    -1.92
     gouvernements
    -1.92
     lèvres
    -1.88
     navires
    -1.88
     leçons
    -1.88
     vérit
    -1.87
     vœux
    -1.87
     oreilles
    -1.86
    POSITIVE LOGITS
    ſelves
    1.13
     myſelf
    1.09
     lances
    1.09
     themſelves
    1.09
     ―――――
    1.07
    BibitemShut
    1.03
     doubtnut
    1.01
     Theſe
    1.00
     basses
    1.00
     itſelf
    1.00
    Activations Density 0.375%

    No Known Activations