© 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. 15182
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by the word "way" or discuss relationships ending.

    oai_token-act-pair · gemini-2.0-flash

    way

    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
    twimg
    -0.83
    Становништво
    -0.69
    RUnlock
    -0.61
    ]]:
    -0.60
    enumii
    -0.60
    ApiModelProperty
    -0.59
    ustimmung
    -0.58
     Chwiliwch
    -0.57
    ụy
    -0.56
    NUMX
    -0.55
    POSITIVE LOGITS
     way
    1.55
    way
    1.13
     Way
    1.09
    Way
    1.08
     WAY
    1.02
     ways
    0.93
    WAY
    0.88
     manier
    0.78
     maneira
    0.75
     manera
    0.73
    Activations Density 1.073%

    No Known Activations