© 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. 14283
    Prev
    Next
    INDEX
    Explanations

    legal language related to defamation and workplace issues

    oai_token-act-pair · gemini-2.0-flash

    legal proceedings

    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
    슷
    -0.58
    NECTION
    -0.54
    kháu
    -0.54
     Cuff
    -0.50
    etka
    -0.50
    apparent
    -0.50
    läs
    -0.50
    savings
    -0.49
    __":
    -0.49
    recogn
    -0.48
    POSITIVE LOGITS
     libel
    0.75
     slander
    0.73
    Rüyada
    0.67
     rumor
    0.61
     defamation
    0.59
    <bos>
    0.56
    tagHelperRunner
    0.55
    
    0.54
     rumors
    0.54
    谣
    0.54
    Activations Density 1.939%

    No Known Activations