© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14035
    Prev
    Next
    INDEX
    Explanations

    words describing features and designs

    oai_token-act-pair · gemini-2.0-flash

    components and structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     виправивши
    -0.55
    RegistryLite
    -0.52
    IUrlHelper
    -0.52
     "..\..\
    -0.51
    ...>
    -0.50
    Koordinaten
    -0.49
    lccn
    -0.49
    таратура
    -0.49
    encodeWith
    -0.48
    istro
    -0.48
    POSITIVE LOGITS
    IsContent
    0.68
     ujednoznacz
    0.48
    клопе
    0.43
    不堪
    0.43
     are
    0.41
    eradish
    0.40
     tomba
    0.40
     voorzien
    0.39
     Cientí
    0.39
     समीक्षाएं
    0.38
    Activations Density 0.405%

    No Known Activations