© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4726
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal feelings, internal struggles, and self-improvement.

    oai_token-act-pair · gemini-2.0-flash

    deep

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     outside
    -1.90
     Outside
    -1.83
    Outside
    -1.80
    outside
    -1.78
     OUTSIDE
    -1.52
    OUTSIDE
    -1.31
     buiten
    -0.90
     utanför
    -0.90
     exterior
    -0.88
    外面
    -0.82
    POSITIVE LOGITS
     deep
    2.41
    deep
    1.95
    Deep
    1.86
     Deep
    1.86
     DEEP
    1.81
    DEEP
    1.55
     diep
    1.33
     deeper
    1.30
     profundas
    1.30
     deepest
    1.27
    Activations Density 11.821%

    No Known Activations