© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4906
    Prev
    Next
    INDEX
    Explanations

    a smattering of words that seem to be related to medical imaging, superheroes, basic English, and the letter 'w'

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -0.56
     (!__
    -0.50
    Nya
    -0.50
     kuti
    -0.48
    bladet
    -0.47
     endregion
    -0.44
     bezeichneter
    -0.44
     data
    -0.43
    })();
    -0.43
    oredCriteria
    -0.43
    POSITIVE LOGITS
    ########.
    0.79
    DataAnnotations
    0.71
     Púb
    0.61
     AssemblyCompany
    0.57
    TemporalType
    0.56
    Tē
    0.53
    PMailer
    0.52
    MessageTagHelper
    0.51
     Beek
    0.50
    UserScript
    0.49
    Activations Density 0.132%

    No Known Activations