© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6635
    Prev
    Next
    INDEX
    Explanations

    mentions of times of day, especially early morning, late afternoon, and evenings

    oai_token-act-pair · gemini-2.0-flash

    times of day

    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
     myſelf
    -1.52
     Efq
    -1.46
     Majefty
    -1.39
     Jefus
    -1.35
     themſelves
    -1.34
     Diſ
    -1.33
     purpoſe
    -1.31
     Houſe
    -1.30
     ſtate
    -1.27
     houſe
    -1.27
    POSITIVE LOGITS
     
    0.50
     M
    0.49
    <eos>
    0.46
     P
    0.45
     shift
    0.44
     F
    0.44
     B
    0.43
    M
    0.42
     L
    0.42
    ↵
    0.42
    Activations Density 1.949%

    No Known Activations