© 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. 9655
    Prev
    Next
    INDEX
    Explanations

    code documentation tags in Java such as @param, @return, @code, @link, @Nullable, @Nonnull, and some html tags

    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
    GEBURTSDATUM
    -1.29
    StoryboardSegue
    -1.29
    EndGlobalSection
    -1.16
     AssemblyCulture
    -1.11
    SharedDtor
    -1.03
    dafx
    -1.02
     Италијани
    -1.02
    OGND
    -1.01
     Мексичка
    -1.00
    LookAnd
    -1.00
    POSITIVE LOGITS
    li
    0.59
    re
    0.55
    ti
    0.51
    C
    0.49
    B
    0.48
    th
    0.48
    h
    0.47
    ba
    0.47
    sur
    0.47
    dev
    0.47
    Activations Density 1.671%

    No Known Activations