© 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. 15232
    Prev
    Next
    INDEX
    Explanations

    words related to constraints, difficulties and length of time

    oai_token-act-pair · gemini-2.0-flash

    Difficulty or length

    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
     cherchés
    -1.02
    🏾
    -0.74
    DeleteBehavior
    -0.73
    Izvori
    -0.73
     виправивши
    -0.72
    🏿
    -0.71
    🏽
    -0.71
     CreateTagHelper
    -0.70
    AddTagHelper
    -0.69
     overkill
    -0.68
    POSITIVE LOGITS
     avoient
    0.66
     habet
    0.57
     vertes
    0.56
     tillgäng
    0.51
     commerciales
    0.50
     feroit
    0.50
     chré
    0.49
    times
    0.49
     pitié
    0.48
    <bos>
    0.48
    Activations Density 1.903%

    No Known Activations