© 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. 13027
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the potential for future impact

    oai_token-act-pair · gemini-2.0-flash

    words relating to potential or prospects

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

    potential

    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
     <=",
    -0.96
    GEBURTSDATUM
    -0.92
    ValueStyle
    -0.81
    ConstraintMaker
    -0.79
    
    -0.76
     tartalomajánló
    -0.75
    
    -0.75
    AddTagHelper
    -0.75
    XtraEditors
    -0.74
    IntoConstraints
    -0.72
    POSITIVE LOGITS
     for
    0.81
    for
    0.58
    For
    0.53
     gew
    0.50
     For
    0.49
     FOR
    0.48
     für
    0.47
     dla
    0.44
     flow
    0.44
    forall
    0.44
    Activations Density 10.524%

    No Known Activations