© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4606
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "common", often about things shared between multiple parties

    oai_token-act-pair · gemini-2.0-flash

    common

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Exacts
    -0.66
    EndInit
    -0.63
     gynhyrchwyd
    -0.61
    SharedDtor
    -0.61
    expandindo
    -0.59
     '\\;'
    -0.59
    LabelTagHelper
    -0.57
    MethodManager
    -0.57
    DockStyle
    -0.57
     muualla
    -0.53
    POSITIVE LOGITS
     common
    2.06
    common
    1.78
     Common
    1.74
    Common
    1.68
     COMMON
    1.54
    COMMON
    1.40
     común
    1.38
     comunes
    1.34
     comum
    1.27
     shared
    1.15
    Activations Density 1.213%

    No Known Activations