© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11052
    Prev
    Next
    INDEX
    Explanations

    mentions of frequency of consumption or medication, often including "times" and units of time.

    oai_token-act-pair · gemini-2.0-flash

    frequency and measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     tibi
    -0.55
     européens
    -0.53
    Портал
    -0.50
    kloped
    -0.49
     habet
    -0.48
    بوابة
    -0.47
     couverts
    -0.46
     Tonga
    -0.45
     Crock
    -0.45
    BeginInit
    -0.45
    POSITIVE LOGITS
     a
    0.84
    geable
    0.57
     p
    0.57
    pé
    0.54
    kyou
    0.54
    printStackTrace
    0.53
    Analog
    0.53
    #![
    0.52
    nadequate
    0.50
     Analog
    0.50
    Activations Density 6.159%

    No Known Activations