© 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. 5489
    Prev
    Next
    INDEX
    Explanations

    the name "Robert" or nickname "Bob"

    oai_token-act-pair · gemini-2.0-flash

    Robert/Bob

    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
    IBarButtonItem
    -0.65
     noqa
    -0.65
     Aristi
    -0.64
    ItemBackground
    -0.64
    PhysRev
    -0.64
     useAppContext
    -0.63
    archiviato
    -0.63
     detergents
    -0.63
     improvis
    -0.61
     hybridization
    -0.61
    POSITIVE LOGITS
     defaultstate
    0.51
    adt
    0.50
     Wal
    0.46
    %)$
    0.46
     Un
    0.45
     En
    0.45
     S
    0.43
     E
    0.42
    ective
    0.42
    Wal
    0.40
    Activations Density 0.393%

    No Known Activations