© 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. 15525
    Prev
    Next
    INDEX
    Explanations

    Korean names, numbers, and series title casing

    oai_token-act-pair · gemini-2.0-flash

    calculations and names

    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
    ⓧ
    -0.87
     propOrder
    -0.80
    InjectAttribute
    -0.78
    rungsseite
    -0.78
    AutoScale
    -0.78
     nahilalakip
    -0.78
    MigrationBuilder
    -0.76
    IntoConstraints
    -0.76
     Paglinawan
    -0.76
     defaultstate
    -0.75
    POSITIVE LOGITS
    šne
    0.44
    acağ
    0.44
     Inc
    0.43
    ing
    0.43
    jean
    0.40
     Live
    0.40
    OCK
    0.40
     angesch
    0.40
     Wan
    0.39
    </thead>
    0.39
    Activations Density 9.230%

    No Known Activations