© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15369
    Prev
    Next
    INDEX
    Explanations

    legal language about evidence and demonstrating facts

    oai_token-act-pair · gemini-2.0-flash

    show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    IntoConstraints
    -0.77
    Personensuche
    -0.75
    SourceChecksum
    -0.70
    istoitu
    -0.69
     nôtre
    -0.69
     متعلقه
    -0.68
    /**
    -0.64
    сылкі
    -0.62
    ädie
    -0.62
     enfans
    -0.62
    POSITIVE LOGITS
     convincing
    0.52
    vincing
    0.50
    phosa
    0.49
    theros
    0.49
    erialized
    0.48
     ability
    0.48
    numerusform
    0.47
     manif
    0.47
    tagHelperRunner
    0.47
     convincingly
    0.47
    Activations Density 2.362%

    No Known Activations