© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5670
    Prev
    Next
    INDEX
    Explanations

    words related to accidents, crime and injury with some words relating to legal culpability and some code

    oai_token-act-pair · gemini-2.0-flash

    snippets of language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     سكانية
    -0.65
    +#+#
    -0.57
     nahilalakip
    -0.56
    MigrationBuilder
    -0.55
    شهاد
    -0.54
    SourceChecksum
    -0.54
     "));
    -0.54
    Спољашње
    -0.54
    adpleegd
    -0.52
    RefNanny
    -0.52
    POSITIVE LOGITS
     ​​
    1.02
    amp
    0.54
     
    0.54
     gesti
    0.54
      
    0.54
     adipis
    0.50
     للاسماء
    0.49
    providedIn
    0.49
     Inscrivez
    0.47
     Faites
    0.46
    Activations Density 40.265%

    No Known Activations