© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15495
    Prev
    Next
    INDEX
    Explanations

    terms related to social activities and locations

    oai_token-act-pair · gemini-2.0-flash

    places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ActionCreators
    -0.56
    TagMode
    -0.51
    unex
    -0.49
    EMO
    -0.48
    rabble
    -0.48
     extrême
    -0.48
     Television
    -0.48
    سک
    -0.48
    سع
    -0.47
    kirchen
    -0.46
    POSITIVE LOGITS
    verwijspagina
    0.78
    RenderAtEndOf
    0.71
    tvguidetime
    0.69
    Portale
    0.63
     ContentValues
    0.61
    ValueStyle
    0.61
    SharedCtor
    0.60
    ContentLoaded
    0.60
    rrggbb
    0.60
    yntaxException
    0.59
    Activations Density 1.420%

    No Known Activations