© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13018
    Prev
    Next
    INDEX
    Explanations

    words related to illumination and lights, particularly LED lights

    oai_token-act-pair · gemini-2.0-flash

    lighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    etheless
    -0.64
    titial
    -0.58
    tyle
    -0.57
    Биография
    -0.56
    Série
    -0.55
     obstante
    -0.55
    payer
    -0.54
    lihatkan
    -0.53
     Sturgeon
    -0.53
     entanto
    -0.53
    POSITIVE LOGITS
     AssemblyVersion
    0.78
    bootstrapcdn
    0.77
     zvuky
    0.69
    kloped
    0.66
    ><?
    0.65
    lexia
    0.64
    uxxxx
    0.63
    TileEntity
    0.63
    Бахар
    0.61
    multer
    0.60
    Activations Density 1.394%

    No Known Activations