© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12625
    Prev
    Next
    INDEX
    Explanations

    legal cases and investigations

    oai_token-act-pair · gemini-2.0-flash

    investigating cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     مشين
    -0.68
     pleins
    -0.50
     acides
    -0.50
    NOPQRST
    -0.49
     étrangers
    -0.48
    ppincott
    -0.48
     attre
    -0.48
    brities
    -0.48
     existência
    -0.48
    
    -0.47
    POSITIVE LOGITS
     unsolved
    0.75
    <bos>
    0.71
    SOLVED
    0.65
     suspected
    0.63
    XmlAccessType
    0.63
    contentLoaded
    0.60
     investigators
    0.60
     investigations
    0.58
     ddelweddau
    0.58
     alleged
    0.57
    Activations Density 1.423%

    No Known Activations