© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13140
    Prev
    Next
    INDEX
    Explanations

    phrases discussing legal testimony in court or phrases expressing a preference for a specific type of marriage.

    oai_token-act-pair · gemini-2.0-flash

    Common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     esternos
    -0.97
    :✨
    -0.91
     незавершена
    -0.89
     XCTest
    -0.84
    BeginContext
    -0.83
    脚注の使い方
    -0.83
     Monfieur
    -0.83
    __(/*!
    -0.82
     Theſe
    -0.81
    rungsseite
    -0.80
    POSITIVE LOGITS
     full
    0.44
     Sa
    0.43
     vulnerables
    0.41
     Simon
    0.40
    enska
    0.38
    randrange
    0.37
     recognize
    0.37
     West
    0.36
    enas
    0.36
     return
    0.35
    Activations Density 0.738%

    No Known Activations