© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12380
    Prev
    Next
    INDEX
    Explanations

    words with the "somat" prefix or pertaining to locations with unique character combinations

    oai_token-act-pair · gemini-2.0-flash

    Poland

    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
     Prisma
    -0.50
    rieu
    -0.49
    Erfolge
    -0.47
     Estar
    -0.45
     AssemblyProduct
    -0.44
     favorables
    -0.44
    Bien
    -0.44
     ratification
    -0.43
    Demografie
    -0.42
    idue
    -0.42
    POSITIVE LOGITS
    aarrggbb
    0.77
    contentLoaded
    0.65
    setVerticalGroup
    0.63
    ++]=
    0.60
     dAtA
    0.59
    ंदीखरीदारी
    0.55
     cuantos
    0.52
    примеча
    0.52
    TypedDataSet
    0.51
    mergeFrom
    0.51
    Activations Density 0.212%

    No Known Activations