© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    finite verbs

    oai_token-act-pair · gemini-2.0-flash

    reflexive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    vician
    -0.50
     lopp
    -0.47
    initComponents
    -0.46
     reban
    -0.45
    jona
    -0.43
     vapa
    -0.43
    readInt
    -0.42
     bénévol
    -0.42
     görd
    -0.42
     hendes
    -0.42
    POSITIVE LOGITS
     itself
    2.53
     themselves
    2.53
    themselves
    2.39
    itself
    2.36
     herself
    2.30
     himself
    2.20
     Itself
    2.09
    himself
    2.05
    herself
    2.03
     ourselves
    1.95
    Activations Density 2.567%

    No Known Activations