© 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. 3997
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of words across lots of topics and styles, but especially words with capital letters in them

    oai_token-act-pair · gemini-2.0-flash

    Code/Legal document snippets

    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
     th
    -0.80
     t
    -0.78
     thi
    -0.65
     s
    -0.62
     h
    -0.61
     al
    -0.60
     te
    -0.59
     o
    -0.59
     bu
    -0.59
     w
    -0.58
    POSITIVE LOGITS
     ་་
    1.52
     Efq
    1.45
     faſt
    1.38
    ſelf
    1.34
     itſelf
    1.33
     ſind
    1.30
     iſt
    1.30
     Majefty
    1.29
     ―――――
    1.28
     myſelf
    1.28
    Activations Density 0.805%

    No Known Activations