© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9259
    Prev
    Next
    INDEX
    Explanations

    words related to obstacles and problems

    oai_token-act-pair · gemini-2.0-flash

    convenience/inconvenience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     convenience
    -0.74
     convenient
    -0.73
     inconvenient
    -0.71
    Convenient
    -0.70
    convenient
    -0.69
     conveniences
    -0.65
    方便
    -0.64
    convenience
    -0.63
     inconvenience
    -0.61
     wygod
    -0.59
    POSITIVE LOGITS
    horabuena
    0.67
    openConnection
    0.66
     BoxFit
    0.65
     BoxDecoration
    0.60
     Eſ
    0.59
     Forumite
    0.57
    createCanvas
    0.57
     Teg
    0.56
    ouncil
    0.54
     يتيمه
    0.53
    Activations Density 21.283%

    No Known Activations