© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5420
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and helpfulness

    oai_token-act-pair · gemini-2.0-flash

    helpful useful

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Lähteet
    -0.75
    ########.
    -0.71
     مشين
    -0.70
    OGND
    -0.68
    quelize
    -0.66
    Sucesor
    -0.64
    setVerticalGroup
    -0.64
     kaynağından
    -0.64
    JspWriter
    -0.64
    TintMode
    -0.62
    POSITIVE LOGITS
     helpful
    1.71
     useful
    1.70
    useful
    1.50
    helpful
    1.49
     Useful
    1.49
     Helpful
    1.43
    Useful
    1.40
     help
    1.34
    Helpful
    1.33
     usefulness
    1.27
    Activations Density 1.444%

    No Known Activations