© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10819
    Prev
    Next
    INDEX
    Explanations

    hyphenated IDs that look like 'polymers-0-0-0-15x9-y0-0-0-z' followed by a bracketed explanation

    oai_token-act-pair · gemini-2.0-flash

    Non-English identifiers

    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
    ers
    -0.59
    ATURES
    -0.57
    iso
    -0.57
     hen
    -0.56
    inthe
    -0.56
    ari
    -0.56
    we
    -0.56
    is
    -0.55
     noDo
    -0.54
     bởi
    -0.53
    POSITIVE LOGITS
     Савезне
    0.78
    IUrlHelper
    0.73
    InjectAttribute
    0.64
    Geplaatst
    0.64
    DeleteBehavior
    0.63
    ніципа
    0.60
    extAlignment
    0.60
     AspNetCore
    0.60
     Paglinawan
    0.59
    bewerken
    0.59
    Activations Density 0.791%

    No Known Activations