© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5370
    Prev
    Next
    INDEX
    Explanations

    scientific observations and what can be concluded from them

    oai_token-act-pair · gemini-2.0-flash

    observe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     observation
    -2.39
     observed
    -2.34
     observe
    -2.19
     observing
    -2.14
     observations
    -2.14
     Observation
    -2.09
     observes
    -2.08
     Observed
    -2.03
    observed
    -2.03
    observation
    -2.02
    POSITIVE LOGITS
    ynb
    0.63
     iſt
    0.61
    makeText
    0.60
     AssemblyTitle
    0.59
     يتيمه
    0.59
    univ
    0.56
     stipend
    0.56
     calculator
    0.56
    Erreferentziak
    0.53
    MENAFN
    0.53
    Activations Density 1.651%

    No Known Activations