© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13512
    Prev
    Next
    INDEX
    Explanations

    words associated with objectives and strategies

    oai_token-act-pair · gemini-2.0-flash

    terms related to goal-setting

    np_token-act-pair-logits · gpt-4o-mini

    goal/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_21/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.21.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
    Datuak
    -0.75
    
    -0.74
     SqlCommand
    -0.65
     MainAxisSize
    -0.63
    ReusableCell
    -0.62
    IntoConstraints
    -0.59
    FunctionFlags
    -0.59
    prepareStatement
    -0.58
    URLException
    -0.57
     Administrativna
    -0.57
    POSITIVE LOGITS
     setting
    0.65
     Setting
    0.63
     Set
    0.62
     sets
    0.57
     set
    0.57
    Set
    0.56
    set
    0.54
    setting
    0.52
    Setting
    0.52
     Sets
    0.52
    Activations Density 3.785%

    No Known Activations