© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15360
    Prev
    Next
    INDEX
    Explanations

    legal or formal writing

    oai_token-act-pair · gemini-2.0-flash

    code and book mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    einem
    -0.68
    Gambas
    -0.65
    ècie
    -0.64
     prestazioni
    -0.64
    }`).
    -0.63
    Насе
    -0.63
     betweenstory
    -0.63
     teórico
    -0.63
     kimdir
    -0.62
     varandra
    -0.61
    POSITIVE LOGITS
     Popular
    0.50
    chay
    0.50
    Popular
    0.49
     palav
    0.48
    diano
    0.46
    Dav
    0.46
    السكان
    0.45
     pla
    0.44
     popular
    0.44
     Offisielt
    0.43
    Activations Density 3.805%

    No Known Activations