© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3131
    Prev
    Next
    INDEX
    Explanations

    sentences using the verb "is," especially when describing a scene or situation

    oai_token-act-pair · gemini-2.0-flash

    looking or shaping

    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
     ***!
    -0.52
     MonoBehaviour
    -0.50
    AndUpdate
    -0.50
    PRNewswire
    -0.50
    tagext
    -0.49
    ValueStyle
    -0.48
     تانيه
    -0.48
    Xaml
    -0.48
    Autowired
    -0.47
    CrossRef
    -0.46
    POSITIVE LOGITS
     looking
    1.11
     shaping
    1.06
    looking
    0.92
     Looking
    0.85
     LOOKING
    0.82
     Shaping
    0.77
     look
    0.77
     lookin
    0.76
     shapes
    0.74
     looks
    0.73
    Activations Density 2.185%

    No Known Activations