© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12184
    Prev
    Next
    INDEX
    Explanations

    mentions of the weather and associated activities

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Normdatei
    -1.03
     rained
    -0.84
     raining
    -0.79
     rains
    -0.77
     rain
    -0.77
     snow
    -0.71
    Rain
    -0.69
    ніципалі
    -0.68
    protoimpl
    -0.68
     Rain
    -0.68
    POSITIVE LOGITS
     nice
    0.93
     beautiful
    0.78
     fine
    0.73
     Nice
    0.72
    nice
    0.72
    Nice
    0.68
     lovely
    0.66
     nicer
    0.66
     schönen
    0.63
     nicest
    0.63
    Activations Density 0.991%

    No Known Activations