© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6995
    Prev
    Next
    INDEX
    Explanations

    sentences using "that", "to", "will", "can", "may", and pronouns referencing people

    oai_token-act-pair · gemini-2.0-flash

    record

    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
    inheritdoc
    -0.50
     propOrder
    -0.49
    InstrumentedTest
    -0.47
    pair
    -0.47
    complexContent
    -0.46
     nasel
    -0.46
     pair
    -0.45
    gemene
    -0.45
     Thessalon
    -0.45
    WriteBarrier
    -0.44
    POSITIVE LOGITS
     record
    1.98
     Record
    1.70
    record
    1.63
    Record
    1.49
     RECORD
    1.34
     records
    1.30
     récord
    1.13
     Records
    1.11
    Records
    1.09
     RECORDS
    1.08
    Activations Density 7.348%

    No Known Activations