© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14923
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings, especially those involving conviction and appeals

    oai_token-act-pair · gemini-2.0-flash

    legal or judicial terminology

    np_token-act-pair-logits · gpt-4o-mini

    New York related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     doInBackground
    -0.65
     Mohawk
    -0.62
     BoxDecoration
    -0.61
     DBNull
    -0.61
    raszamy
    -0.57
    ArgsConstructor
    -0.57
     <=",
    -0.55
     rage
    -0.53
    TagHelper
    -0.52
     getItemCount
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.67
    fromnode
    0.50
    ContentAsync
    0.49
    chall
    0.48
    évaluateur
    0.47
    Imp
    0.47
    τισ
    0.46
     թվական
    0.46
     ◄
    0.45
     Penh
    0.45
    Activations Density 0.762%

    No Known Activations