© 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. 10934
    Prev
    Next
    INDEX
    Explanations

    action verbs with past tense forms

    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
    Their
    -0.77
     Their
    -0.75
     deres
    -0.71
    their
    -0.65
     their
    -0.62
    Its
    -0.60
     Jej
    -0.59
     Its
    -0.58
     THEIR
    -0.58
     ihrer
    -0.57
    POSITIVE LOGITS
     himself
    1.48
     his
    1.45
    himself
    1.29
    his
    1.04
     himſelf
    0.90
     zijn
    0.82
    viewDidLoad
    0.82
    zijn
    0.82
     istrinya
    0.81
     <<<<<<<<<<<<<<
    0.77
    Activations Density 12.818%

    No Known Activations