© 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. 4557
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs related to someone departing or related words such as trips

    oai_token-act-pair · gemini-2.0-flash

    leave

    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
     تانيه
    -0.51
    delning
    -0.48
     erken
    -0.47
     fibrillation
    -0.43
     páns
    -0.42
     mismas
    -0.42
    íncia
    -0.40
     mismos
    -0.40
    statin
    -0.40
     casó
    -0.40
    POSITIVE LOGITS
     intptr
    0.79
     the
    0.77
    httphttps
    0.68
     autorytatywna
    0.67
     StatefulWidget
    0.67
    BagLayout
    0.66
     our
    0.62
    afficheront
    0.60
     his
    0.60
    quently
    0.59
    Activations Density 12.964%

    No Known Activations