© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    a series of common words frequently used in complex English sentences

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     يتيمه
    -0.82
     ModelExpression
    -0.82
     pinulongan
    -0.75
    writeFieldEnd
    -0.75
    :✨
    -0.73
    BeginContext
    -0.73
     nahilalakip
    -0.70
    tonsoft
    -0.69
     CreateTagHelper
    -0.66
     Familienname
    -0.64
    POSITIVE LOGITS
    ')}}"
    0.50
     lenker
    0.44
    벽
    0.41
    limus
    0.40
    рация
    0.40
    ρών
    0.40
    umpulan
    0.39
    graphiques
    0.39
     dou
    0.38
    ecal
    0.38
    Activations Density 2.234%

    No Known Activations