© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3124
    Prev
    Next
    INDEX
    Explanations

    language related to economics and the law

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     purpoſe
    -0.79
    ſelf
    -0.76
    enumii
    -0.74
    Personendaten
    -0.74
     pleaſure
    -0.73
     reaſon
    -0.70
    ImageContext
    -0.70
     ſind
    -0.69
     ſmall
    -0.68
     Jefus
    -0.68
    POSITIVE LOGITS
     so
    0.64
     vide
    0.56
     I
    0.56
     pinulongan
    0.53
     in
    0.53
     under
    0.52
    /
    0.49
    Lato
    0.48
     He
    0.48
    toMatch
    0.47
    Activations Density 6.180%

    No Known Activations