© 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. 12046
    Prev
    Next
    INDEX
    Explanations

    words that relate to time, positions, pronouns, and logical conditions within a text.

    oai_token-act-pair · 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
     feroit
    -0.63
     ainfi
    -0.61
     avoient
    -0.60
     enfans
    -0.59
     vérit
    -0.56
     auroit
    -0.56
     étoient
    -0.56
     varandra
    -0.53
    "):
    -0.53
     leçons
    -0.53
    POSITIVE LOGITS
     Whigs
    0.48
     Whig
    0.46
     compilations
    0.45
     employes
    0.43
     dwelt
    0.41
     hereof
    0.41
     discontinuities
    0.41
     alibi
    0.40
     informants
    0.40
     chronological
    0.40
    Activations Density 51.430%

    No Known Activations