© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11473
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'he' and words related to government and law

    oai_token-act-pair · gemini-2.0-flash

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     he
    -2.22
     she
    -1.34
    He
    -1.32
     He
    -1.23
    he
    -1.10
     он
    -1.10
     він
    -0.99
    彼は
    -0.94
     him
    -0.85
    she
    -0.84
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    AddTagHelper
    0.81
     resourceCulture
    0.80
     فريبيس
    0.73
     Signalez
    0.69
    MessageState
    0.66
     kaarangay
    0.66
    tanleria
    0.65
    awtextra
    0.65
    !*\
    0.65
    Activations Density 1.798%

    No Known Activations