© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5258
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be" (is, was, are, etc.) in various tenses

    oai_token-act-pair · gemini-2.0-flash

    Diary entries

    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
     it
    -0.70
    it
    -0.60
    It
    -0.59
     It
    -0.59
     nó
    -0.54
     оно
    -0.49
     которое
    -0.44
    它
    -0.41
     它
    -0.39
    ět
    -0.38
    POSITIVE LOGITS
    StoryboardSegue
    0.94
     defaultstate
    0.90
    تقاوى
    0.86
     &___
    0.82
    rungsseite
    0.79
    Geplaatst
    0.78
    contentLoaded
    0.77
     Jefus
    0.77
     nakalista
    0.77
     utafitiHapana
    0.77
    Activations Density 1.976%

    No Known Activations