© 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. 12861
    Prev
    Next
    INDEX
    Explanations

    instances of question/answer formats and references to figures or diagrams with labels

    oai_token-act-pair · gemini-2.0-flash

    a and colon

    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
    MVH
    -0.54
    onoi
    -0.50
    numerusform
    -0.50
     Fiction
    -0.48
    UVWXYZ
    -0.48
    地说
    -0.47
    зец
    -0.47
    )\}
    -0.47
     Bunting
    -0.47
     insert
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.65
    WebElementEntity
    0.65
     AssemblyVersion
    0.63
    Tikang
    0.61
    iastes
    0.60
    Хьажоргаш
    0.59
     Meksiku
    0.58
     CreateTagHelper
    0.56
    rungsseite
    0.54
     NUKAT
    0.54
    Activations Density 2.770%

    No Known Activations