© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5951
    Prev
    Next
    INDEX
    Explanations

    the pronoun "you," along with related words like "your" and "yourselves."

    oai_token-act-pair · gemini-2.0-flash

    Addresses the reader

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     I
    -0.49
     Roskov
    -0.43
     étoient
    -0.43
    izowane
    -0.43
     aufgestellt
    -0.42
     berakhir
    -0.41
     gegeben
    -0.41
    SharedDtor
    -0.40
    <bos>
    -0.39
     )
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.88
    GEBURTSDATUM
    0.74
    modelBuilder
    0.71
     EconPapers
    0.71
    AutoScaleMode
    0.65
    ISupport
    0.65
    EndInit
    0.62
    AndEndTag
    0.62
    Gön
    0.61
    ⓧ
    0.60
    Activations Density 20.500%

    No Known Activations