© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10644
    Prev
    Next
    INDEX
    Explanations

    commas near certain words like "the," "we," "users," "effort," "avoid" but mostly just commas.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     themselves
    -0.50
     benefit
    -0.50
    idak
    -0.48
    ]>=
    -0.45
    }{$
    -0.45
     himself
    -0.44
    يكب
    -0.43
    anie
    -0.42
     itself
    -0.41
    ]._
    -0.41
    POSITIVE LOGITS
     EconPapers
    0.95
     Савезне
    0.75
     StatefulWidget
    0.71
     InputDecoration
    0.69
    Personendaten
    0.69
     MessageBoxIcon
    0.68
    endenza
    0.66
    oredCriteria
    0.66
     Normdatei
    0.66
     GenerationType
    0.65
    Activations Density 0.281%

    No Known Activations