© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5630
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that the current study or result is novel

    oai_token-act-pair · gemini-2.0-flash

    the first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     for
    -0.55
     was
    -0.50
     
    -0.43
     nâng
    -0.42
     Le
    -0.42
     último
    -0.41
     last
    -0.40
     becoming
    -0.39
    c
    -0.39
     it
    -0.38
    POSITIVE LOGITS
    Personensuche
    1.31
     المعيارى
    1.03
     resourceCulture
    0.95
     GenerationType
    0.92
    httphttps
    0.91
     otomatig
    0.90
     ContentValues
    0.86
     StatelessWidget
    0.86
     AspNetCore
    0.85
     esternos
    0.85
    Activations Density 0.765%

    No Known Activations