© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1088
    Prev
    Next
    INDEX
    Explanations

    a variety of terms that seem to be related to several narrowly defined topics

    oai_token-act-pair · gemini-2.0-flash

    technical issue in French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     linear
    -0.55
    alnız
    -0.53
     TÉCN
    -0.52
     Jir
    -0.52
    otrop
    -0.52
     getResources
    -0.50
     Tit
    -0.50
    )}>
    -0.49
     inertia
    -0.48
    ?,?,
    -0.48
    POSITIVE LOGITS
     estekak
    0.81
    RTEX
    0.81
     Wicidata
    0.69
    出版年
    0.69
    webElementGuid
    0.66
     AssemblyCulture
    0.63
    WithIOException
    0.62
    Personensuche
    0.59
    +:+
    0.58
     ModelExpression
    0.58
    Activations Density 10.322%

    No Known Activations