© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11269
    Prev
    Next
    INDEX
    Explanations

    seems to be identifying punctuation and structural elements within text, possibly delineating sentences or phrases with heightened activation at the very end of sections

    oai_token-act-pair · gemini-2.0-flash

    period punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ſtate
    -0.69
     ftate
    -0.61
     NDEBUG
    -0.60
     fubject
    -0.57
     Rupert
    -0.57
     laſt
    -0.56
    ResponseWriter
    -0.56
     beſt
    -0.56
     houſe
    -0.56
     Jefus
    -0.54
    POSITIVE LOGITS
    SharedDtor
    0.68
    MigrationBuilder
    0.67
    Personendaten
    0.60
     ModelExpression
    0.56
    <bos>
    0.54
     demografica
    0.54
    ंदीखरीदारी
    0.53
    windowFixed
    0.52
    verwijspagina
    0.50
    }")
    0.49
    Activations Density 23.882%

    No Known Activations