© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6290
    Prev
    Next
    INDEX
    Explanations

    technical academic papers in astrophysics and cosmology

    oai_token-act-pair · gemini-2.0-flash

    CMB lensing

    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
    setVerticalGroup
    -0.65
    kuuta
    -0.62
     Meksiku
    -0.61
    #+#
    -0.55
     grand
    -0.55
    findpost
    -0.55
    grand
    -0.54
     مرئيه
    -0.53
    cteur
    -0.53
    Datuak
    -0.53
    POSITIVE LOGITS
    الإنجليزية
    0.59
    dengar
    0.57
     TextAppearance
    0.52
     bø
    0.52
     igenom
    0.50
    sizeCache
    0.50
     mør
    0.48
    awin
    0.48
     traceback
    0.48
    jadinya
    0.47
    Activations Density 2.714%

    No Known Activations