© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13632
    Prev
    Next
    INDEX
    Explanations

    information related to academic publications in the machine learning field

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    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
    enumi
    -0.69
    ſelf
    -0.68
     Transvaal
    -0.68
     Siamese
    -0.66
    niająca
    -0.66
    balleur
    -0.64
     ويكيميديا
    -0.62
     Presbyter
    -0.60
    ſelves
    -0.60
     gynhyrchwyd
    -0.60
    POSITIVE LOGITS
     ll
    0.50
     Segal
    0.44
    kap
    0.42
    ongs
    0.42
     Bre
    0.41
     Select
    0.41
    tero
    0.41
     par
    0.41
    og
    0.40
     à
    0.40
    Activations Density 2.820%

    No Known Activations