© 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. 15097
    Prev
    Next
    INDEX
    Explanations

    descriptions of when places, especially restaurants and markets, are open

    oai_token-act-pair · gemini-2.0-flash

    early

    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
     Afternoon
    -0.77
    Afternoon
    -0.65
     abends
    -0.64
     onPostExecute
    -0.60
     Tonight
    -0.59
    findpost
    -0.58
     afternoon
    -0.56
    hling
    -0.56
    WebVitals
    -0.55
     evening
    -0.54
    POSITIVE LOGITS
     early
    2.86
    early
    2.67
    Early
    2.56
     Early
    2.41
     EARLY
    2.30
    EARLY
    2.20
     frühen
    1.74
     früh
    1.50
     vroe
    1.50
    早期
    1.45
    Activations Density 1.421%

    No Known Activations