© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14836
    Prev
    Next
    INDEX
    Explanations

    text in languages other than english, especially mixed with code and references to files

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ellas
    -0.92
     elles
    -0.90
     Elles
    -0.84
     które
    -0.81
    Elles
    -0.75
     éstas
    -0.73
     celles
    -0.70
     ktoré
    -0.70
     powinny
    -0.68
     religiosas
    -0.68
    POSITIVE LOGITS
    ReusableCell
    0.62
    UPI
    0.60
    Décès
    0.52
    clés
    0.50
     جد
    0.50
    kuuta
    0.49
    rati
    0.48
    MockMvc
    0.48
    WindowConstants
    0.47
    randomUUID
    0.47
    Activations Density 0.758%

    No Known Activations