© 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. 11088
    Prev
    Next
    INDEX
    Explanations

    words and phrases within a recipe for lemon punch

    oai_token-act-pair · gemini-2.0-flash

    recipes

    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
    UnusedPrivate
    -0.57
    MigrationBuilder
    -0.54
     createSlice
    -0.53
     саны
    -0.52
     jog
    -0.52
    orszá
    -0.49
    insertBefore
    -0.49
     transfieras
    -0.44
    kop
    -0.43
     Bon
    -0.42
    POSITIVE LOGITS
    IsContent
    0.80
    tagHelperRunner
    0.70
    AndEndTag
    0.65
    MessageState
    0.63
    Bibliograf
    0.62
    complexContent
    0.60
     saturation
    0.60
    TintMode
    0.59
    extAlignment
    0.59
     macular
    0.59
    Activations Density 1.591%

    No Known Activations