© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10018
    Prev
    Next
    INDEX
    Explanations

    reasons that are listed and explained

    oai_token-act-pair · gemini-2.0-flash

    reasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     reasons
    -1.54
     reason
    -1.44
     Reasons
    -1.42
    Reasons
    -1.37
    reasons
    -1.34
    REASONS
    -1.28
     REASONS
    -1.27
     raisons
    -1.20
    reason
    -1.20
    Reason
    -1.18
    POSITIVE LOGITS
     calendriers
    0.66
    expandindo
    0.62
    JvmStatic
    0.61
     gyhoeddwyd
    0.61
    JNIEnv
    0.60
     الحره
    0.60
    Зноскі
    0.60
     виправивши
    0.59
     SwiftUI
    0.57
    ագրություններ
    0.56
    Activations Density 1.849%

    No Known Activations