© 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. 3932
    Prev
    Next
    INDEX
    Explanations

    what appear to be citations and other references to external sources

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     Tourisme
    -0.83
     Jefus
    -0.78
    ')")
    -0.77
     Salto
    -0.77
     myſelf
    -0.77
     disponibilités
    -0.76
     Charlemagne
    -0.75
     ใหม่
    -0.74
     Católica
    -0.74
     Addis
    -0.74
    POSITIVE LOGITS
     Gr
    0.51
     Stra
    0.50
     Mand
    0.49
     Bra
    0.48
     Gar
    0.47
    Bur
    0.46
     Wol
    0.46
     Dar
    0.46
     Bor
    0.46
     Gib
    0.45
    Activations Density 3.501%

    No Known Activations