© 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. 3835
    Prev
    Next
    INDEX
    Explanations

    phrases using "of" to describe a superlative state or best option

    oai_token-act-pair · gemini-2.0-flash

    of

    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
     best
    -0.87
     Best
    -0.82
    best
    -0.79
    Best
    -0.78
     BEST
    -0.71
    BEST
    -0.68
    Personendaten
    -0.66
    Datuak
    -0.62
    featureID
    -0.60
    Prefer
    -0.57
    POSITIVE LOGITS
    EndTag
    0.64
     propOrder
    0.59
    AddTagHelper
    0.59
     insuffisamment
    0.58
    ModelAdmin
    0.55
    thole
    0.54
     CreateTagHelper
    0.54
    intios
    0.51
     fondi
    0.51
    herin
    0.50
    Activations Density 2.408%

    No Known Activations