© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9864
    Prev
    Next
    INDEX
    Explanations

    words containing "prov", "proof", or words related to "appropriate"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ivelany
    -0.47
    "?>
    -0.45
    oinette
    -0.45
     Wikipédia
    -0.44
    Pozdrawiam
    -0.44
    thora
    -0.43
     Nautilus
    -0.42
     gezet
    -0.41
    mailto
    -0.41
     Keychain
    -0.41
    POSITIVE LOGITS
    )++;
    0.85
     PROV
    0.81
    prove
    0.78
     Prove
    0.75
     prov
    0.74
    proven
    0.70
    provo
    0.69
    prov
    0.69
     prove
    0.68
    PROV
    0.68
    Activations Density 0.666%

    No Known Activations