© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2083
    Prev
    Next
    INDEX
    Explanations

    words related to theater or musical productions including people involved and stage design

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "stage"

    np_token-act-pair-logits · gpt-4o-mini

    stage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ForValue
    -0.63
    afone
    -0.59
    SequentialGroup
    -0.56
    elemField
    -0.55
    ]!='
    -0.50
    getKeyCode
    -0.49
    úgó
    -0.48
    WriteBarrier
    -0.47
    MockMvc
    -0.47
    )))));
    -0.47
    POSITIVE LOGITS
     stage
    1.09
    stage
    1.00
     Stage
    0.90
    Stage
    0.87
    Scen
    0.85
     STAGE
    0.83
    STAGE
    0.80
     Scen
    0.79
     scenery
    0.73
     scen
    0.73
    Activations Density 1.001%

    No Known Activations