© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4311
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming and corporate management

    oai_token-act-pair · gemini-2.0-flash

    technical definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Gu
    -0.70
    Gu
    -0.62
     gu
    -0.61
    fs
    -0.61
     fs
    -0.57
    gu
    -0.54
    VersionUID
    -0.52
     StatelessWidget
    -0.52
     ser
    -0.52
    writeFieldEnd
    -0.51
    POSITIVE LOGITS
     <=",
    0.69
    !*\
    0.62
     poveznice
    0.62
     Gough
    0.59
    copg
    0.59
     saites
    0.57
     ↓,
    0.57
    CPtr
    0.56
    #+#
    0.56
    dolu
    0.55
    Activations Density 11.466%

    No Known Activations