© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11794
    Prev
    Next
    INDEX
    Explanations

    references to upper and lower bounds

    oai_token-act-pair · gemini-2.0-flash

    upper

    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
     poffible
    -0.81
     poffe
    -0.68
     ſtand
    -0.66
     itſelf
    -0.65
     purpoſe
    -0.64
     himſelf
    -0.63
     ſhe
    -0.63
     reaſon
    -0.63
     tranſ
    -0.62
     ſever
    -0.61
    POSITIVE LOGITS
    IsContent
    0.56
    DoubleQuotes
    0.54
     body
    0.49
     '\\;'
    0.49
     middle
    0.47
     chi̍t
    0.44
    ixas
    0.43
    )](
    0.43
    InvalidProtocol
    0.43
     con
    0.42
    Activations Density 0.831%

    No Known Activations