© 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. 5200
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and related words like "you"

    oai_token-act-pair · gemini-2.0-flash

    conversational text

    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
     like
    -1.00
    like
    -0.86
    Like
    -0.85
     Like
    -0.85
     LIKE
    -0.69
    LIKE
    -0.68
    像
    -0.57
    AccessorTable
    -0.56
     seperti
    -0.56
     say
    -0.55
    POSITIVE LOGITS
     be
    0.70
     continuant
    0.59
    multirow
    0.58
     légales
    0.54
     být
    0.51
     defaultstate
    0.51
    /**
    0.50
     êtres
    0.50
     ویکی‌پدی
    0.49
     быть
    0.49
    Activations Density 0.668%

    No Known Activations