© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6826
    Prev
    Next
    INDEX
    Explanations

    references to time, whether specific or general.

    oai_token-act-pair · gemini-2.0-flash

    variations of "that"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    quels
    -0.89
    Revenir
    -0.56
    UIControlState
    -0.53
    strix
    -0.50
     CreateTagHelper
    -0.48
     quien
    -0.47
    GeneratedMessage
    -0.46
    šanu
    -0.46
    PYX
    -0.46
    quien
    -0.46
    POSITIVE LOGITS
     that
    3.28
    that
    2.13
     bahwa
    1.70
     rằng
    1.63
     bahawa
    1.51
    That
    1.48
     That
    1.45
     dass
    1.38
     THAT
    1.37
     ότι
    1.35
    Activations Density 8.328%

    No Known Activations