© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2318
    Prev
    Next
    INDEX
    Explanations

    words related to metallurgy and material science

    oai_token-act-pair · gemini-2.0-flash

    Melting and boiling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    principalTable
    -0.64
    cotch
    -0.59
     AssemblyCompany
    -0.57
    UnknownFields
    -0.56
    hyrchwyd
    -0.54
     Fatigue
    -0.53
    abetes
    -0.51
    GIVEREF
    -0.51
     stretcher
    -0.50
    geslacht
    -0.49
    POSITIVE LOGITS
     boiling
    0.80
     bubbling
    0.65
     molten
    0.62
     bouillon
    0.59
     melt
    0.57
    boiling
    0.56
     stirring
    0.54
     nakalista
    0.54
     nahilalakip
    0.54
     boil
    0.53
    Activations Density 1.993%

    No Known Activations