© 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. 5115
    Prev
    Next
    INDEX
    Explanations

    phrases in German related to supporting highly qualified research

    oai_token-act-pair · gemini-2.0-flash

    technical jargon and names

    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
     <<<<<<<<<<<<<<
    -0.71
     AssemblyCulture
    -0.69
     &___
    -0.65
    __*/
    -0.59
    次代
    -0.54
    PathParam
    -0.54
    XmlEnum
    -0.54
     ujednoznacz
    -0.54
    ---*/
    -0.52
    </tbody>
    -0.51
    POSITIVE LOGITS
     EconPapers
    0.59
     supérieurs
    0.56
     فريبيس
    0.52
     superiori
    0.49
    insegna
    0.48
     MainAxisSize
    0.47
    Caratter
    0.47
     nostru
    0.47
     Efq
    0.47
     XCTest
    0.46
    Activations Density 0.393%

    No Known Activations