© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10577
    Prev
    Next
    INDEX
    Explanations

    the word "good" and other words related to the quality of something

    oai_token-act-pair · gemini-2.0-flash

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     good
    -2.53
    good
    -2.39
    Good
    -2.31
     Good
    -2.13
    GOOD
    -2.03
     GOOD
    -2.00
     buenas
    -1.55
     buena
    -1.53
     goede
    -1.52
     buenos
    -1.50
    POSITIVE LOGITS
     AssemblyCulture
    0.59
     Abp
    0.54
    jspx
    0.49
    emias
    0.47
    labelledby
    0.46
     colonies
    0.46
     ISTAT
    0.45
    itaires
    0.45
    SerializedSize
    0.45
    ansa
    0.44
    Activations Density 1.112%

    No Known Activations