© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12525
    Prev
    Next
    INDEX
    Explanations

    expressions of feelings, especially joy and peace, often in the context of purpose or calling.

    oai_token-act-pair · gemini-2.0-flash

    positive emotions and purpose

    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
    ftagPool
    -0.78
    tvguidetime
    -0.77
    abestanden
    -0.75
     ویکی‌پدیا
    -0.71
     يتيمه
    -0.71
    BeginInit
    -0.70
     enregistrer
    -0.68
    adaptiveStyles
    -0.66
     صوتيه
    -0.66
     للاسماء
    -0.66
    POSITIVE LOGITS
     measure
    0.41
    _));
    0.40
    ()));
    0.38
     abge
    0.34
    bal
    0.34
    tuur
    0.32
     MEASURE
    0.32
     المع
    0.32
     zur
    0.32
    ()));
    0.31
    Activations Density 1.846%

    No Known Activations