© 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. 15790
    Prev
    Next
    INDEX
    Explanations

    fragments of internet chat logs including usernames and emoticons

    oai_token-act-pair · gemini-2.0-flash

    French pronouns

    np_max-act · gemini-2.0-flash

    French pronouns

    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
     Bucure
    -0.52
     domini
    -0.52
    lı
    -0.50
     for
    -0.49
     собой
    -0.48
    less
    -0.48
    dom
    -0.47
     Nowhere
    -0.46
     włas
    -0.45
    Read
    -0.44
    POSITIVE LOGITS
    存于互联网档案馆
    0.95
    protoimpl
    0.88
     Signalez
    0.88
     <<<<<<<<<<<<<<
    0.87
    WebElementEntity
    0.85
    SequentialGroup
    0.84
     ***!
    0.84
    ChildScrollView
    0.82
     مشين
    0.82
    ynchronously
    0.81
    Activations Density 0.407%

    No Known Activations