© 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. 9693
    Prev
    Next
    INDEX
    Explanations

    finds many different and varying words

    oai_token-act-pair · gemini-2.0-flash

    parts of something

    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
    HtmlAttribute
    -0.86
    MigrationBuilder
    -0.85
     vérit
    -0.78
    SequentialGroup
    -0.76
     travailleurs
    -0.73
     lèvres
    -0.70
    XMLSchema
    -0.68
    enterOuterAlt
    -0.66
     كومونز
    -0.65
    THINGS
    -0.65
    POSITIVE LOGITS
     heads
    0.62
     houses
    0.57
     floors
    0.55
     homes
    0.51
     ranks
    0.50
     laces
    0.50
    yl
    0.50
     votes
    0.48
     lives
    0.48
     folds
    0.47
    Activations Density 3.553%

    No Known Activations