© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3778
    Prev
    Next
    INDEX
    Explanations

    the word 'why'

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

    questions prefaced with "why"

    oai_token-act-pair · gemini-2.0-flash

    Why

    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
    Pfalz
    -0.48
    Pranala
    -0.42
    англ
    -0.41
    oree
    -0.41
     sisält
    -0.40
    ifrance
    -0.40
     Jigsaw
    -0.40
     ώ
    -0.39
    ISMS
    -0.39
    [(
    -0.38
    POSITIVE LOGITS
     they
    1.03
    LookAnd
    1.00
     it
    0.91
     these
    0.90
    MemoryWarning
    0.84
     you
    0.83
     we
    0.81
     getItemId
    0.81
    awtextra
    0.80
     autorytatywna
    0.78
    Activations Density 2.867%

    No Known Activations