© 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. 4774
    Prev
    Next
    INDEX
    Explanations

    first person perspective, especially those expressing confusion or seeking help

    oai_token-act-pair · gemini-2.0-flash

    "to be" verb forms

    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
     MainAxisSize
    -0.98
    KommentareTeilen
    -0.92
     EconPapers
    -0.86
     виправивши
    -0.83
    MemoryWarning
    -0.79
     дописавши
    -0.75
    AccessorTable
    -0.74
    +#+
    -0.73
    RUnlock
    -0.71
    twimg
    -0.71
    POSITIVE LOGITS
     is
    1.71
     are
    1.22
    are
    0.86
     είναι
    0.85
     está
    0.84
     är
    0.77
     êtes
    0.75
    的是
    0.71
     Is
    0.71
     Are
    0.71
    Activations Density 1.789%

    No Known Activations