© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12167
    Prev
    Next
    INDEX
    Explanations

    the word "usually" in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    usually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     schia
    -0.68
     Plutarch
    -0.64
     propter
    -0.63
     anhänger
    -0.62
     passione
    -0.59
     Fascism
    -0.58
     väx
    -0.58
     wohnung
    -0.58
     NAA
    -0.57
     Secondo
    -0.57
    POSITIVE LOGITS
     EconPapers
    0.76
     }:
    0.75
    LayoutStyle
    0.70
    
    0.68
    CloseOperation
    0.68
     дописавши
    0.66
    уда
    0.66
    __":
    0.65
    merate
    0.63
     den
    0.60
    Activations Density 0.980%

    No Known Activations