© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5678
    Prev
    Next
    INDEX
    Explanations

    scientific jargon, especially related to rays, waves, and frequencies

    oai_token-act-pair · gemini-2.0-flash

    science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     démocr
    -1.02
     hâte
    -0.84
     quelcon
    -0.82
     découver
    -0.82
     fermés
    -0.77
     cérami
    -0.73
     élas
    -0.72
     épais
    -0.69
     normaux
    -0.69
     présidenti
    -0.69
    POSITIVE LOGITS
    *=
    0.48
     fission
    0.48
     factorization
    0.48
    -
    0.47
     ccm
    0.47
    stall
    0.46
    ّا
    0.45
    inc
    0.45
     optimisation
    0.45
    =',
    0.45
    Activations Density 22.562%

    No Known Activations