© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12087
    Prev
    Next
    INDEX
    Explanations

    language regarding achieving goals

    oai_token-act-pair · gemini-2.0-flash

    goals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     незавершена
    -0.72
     contextLoads
    -0.62
    ρών
    -0.60
    PyExc
    -0.59
    netbeans
    -0.58
     inquirer
    -0.57
    RegressionTest
    -0.56
    expandindo
    -0.56
     lenker
    -0.54
    usky
    -0.53
    POSITIVE LOGITS
     goals
    0.85
    Goals
    0.76
    SMART
    0.75
    goals
    0.73
     Goals
    0.73
     goal
    0.71
     achievable
    0.70
     GOALS
    0.68
     obiettivi
    0.66
     raggiung
    0.65
    Activations Density 1.160%

    No Known Activations