© 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. 15438
    Prev
    Next
    INDEX
    Explanations

    the word "is" or the contraction "'s" followed by words that suggest advice or a recommendation.

    oai_token-act-pair · gemini-2.0-flash

    importance/value

    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
     pleaſure
    -0.84
     purpoſe
    -0.82
     raiſ
    -0.80
     Jefus
    -0.76
     miſ
    -0.75
    mybatisplus
    -0.75
    الحياه
    -0.71
     ſeveral
    -0.69
     myſelf
    -0.69
     ſever
    -0.68
    POSITIVE LOGITS
     always
    0.64
     ever
    0.57
     vital
    0.48
     worth
    0.47
     altijd
    0.47
     far
    0.47
     |
    0.46
     never
    0.44
     crucial
    0.44
    always
    0.44
    Activations Density 0.301%

    No Known Activations