© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9270
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, especially those indicating possibility or necessity, and contractions with "not"

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     did
    -1.43
     does
    -1.39
     do
    -1.22
    does
    -1.09
    did
    -1.09
     Does
    -1.07
     Did
    -1.07
     DID
    -1.05
    Does
    -1.04
    Did
    -1.01
    POSITIVE LOGITS
    .
    0.76
    ;
    0.69
    ?
    0.62
    !
    0.57
    ].
    0.50
    ,
    0.50
    !!
    0.49
     öne
    0.49
    惜
    0.49
     championnat
    0.46
    Activations Density 1.868%

    No Known Activations