© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5061
    Prev
    Next
    INDEX
    Explanations

    math equations and some strings of random characters

    oai_token-act-pair · gemini-2.0-flash

    code/math notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    instancetype
    -0.61
    TargetException
    -0.58
    出版年
    -0.56
    koin
    -0.55
    peutic
    -0.49
     Pan
    -0.49
     letra
    -0.48
    ){$
    -0.48
     sembler
    -0.47
    IsContent
    -0.46
    POSITIVE LOGITS
    elemField
    0.71
    NameInMap
    0.68
     ComVisible
    0.65
    IndentedString
    0.64
    ab
    0.63
    styleType
    0.62
    Personensuche
    0.62
     ab
    0.59
     pinulongan
    0.59
     ABN
    0.59
    Activations Density 3.238%

    No Known Activations