© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11643
    Prev
    Next
    INDEX
    Explanations

    legal documents and language

    oai_token-act-pair · gemini-2.0-flash

    legal context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    twimg
    -0.64
     ComVisible
    -0.51
     Taktlose
    -0.51
    NewGuid
    -0.51
     ModelExpression
    -0.50
     Irish
    -0.50
     oot
    -0.50
    leby
    -0.49
     hObject
    -0.48
     CiNii
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.69
    ]--;
    0.64
    testens
    0.58
     насељу
    0.54
     Ton
    0.52
    VIAF
    0.51
     endforeach
    0.50
    findpost
    0.50
     Lat
    0.49
     La
    0.48
    Activations Density 7.698%

    No Known Activations