© 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. 5905
    Prev
    Next
    INDEX
    Explanations

    commas, mentions of tea, and related words.

    oai_token-act-pair · gemini-2.0-flash

    strong

    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
    queryInterface
    -0.97
    UnsafeEnabled
    -0.93
    GEBURTSDATUM
    -0.89
    findpost
    -0.88
     jScrollPane
    -0.87
     saites
    -0.86
    ########.
    -0.84
     autorytatywna
    -0.83
    exitRule
    -0.83
     صوتيه
    -0.82
    POSITIVE LOGITS
     strong
    0.63
     stronger
    0.63
     Strong
    0.57
    strong
    0.57
     Stronger
    0.56
    Strong
    0.56
     strongest
    0.51
     added
    0.50
     STRONG
    0.49
    added
    0.47
    Activations Density 1.729%

    No Known Activations