© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10945
    Prev
    Next
    INDEX
    Explanations

    training, coaching, and assistance

    oai_token-act-pair · gemini-2.0-flash

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     training
    -2.47
    Training
    -2.25
     Training
    -2.23
    training
    -2.20
     TRAINING
    -2.06
    TRAINING
    -1.80
     Trainings
    -1.66
     treinamento
    -1.57
     trainings
    -1.53
     entrenamiento
    -1.51
    POSITIVE LOGITS
     الاطلاع
    0.52
     }}"></
    0.51
     inggris
    0.50
     gekomen
    0.50
    prüche
    0.48
    DOCTYPE
    0.47
     linkovi
    0.47
    enumi
    0.47
     aproximada
    0.45
    calipsis
    0.45
    Activations Density 5.191%

    No Known Activations