© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10795
    Prev
    Next
    INDEX
    Explanations

    time durations (days, week, months and years) and amounts (mg/kg, %, times).

    oai_token-act-pair · gemini-2.0-flash

    duration of time

    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
    -1.31
     Monfieur
    -1.26
     للمعارف
    -1.25
     itſelf
    -1.22
     Efq
    -1.19
     purpoſe
    -1.13
     Theſe
    -1.13
     ſtate
    -1.11
     Jefus
    -1.11
     uſed
    -1.09
    POSITIVE LOGITS
     
    0.67
     to
    0.53
    2
    0.53
     years
    0.52
     (
    0.52
     business
    0.51
     i
    0.51
     days
    0.50
    9
    0.50
    1
    0.49
    Activations Density 7.814%

    No Known Activations