© 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. 1937
    Prev
    Next
    INDEX
    Explanations

    instances of the word "us" or forms of the word "tell."

    oai_token-act-pair · gemini-2.0-flash

    us

    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
     us
    -1.82
    us
    -1.43
    uses
    -1.24
     Us
    -1.23
    Us
    -1.20
    uso
    -1.11
    usar
    -1.06
    use
    -1.02
    ús
    -1.01
    usk
    -1.00
    POSITIVE LOGITS
     as
    0.53
     UN
    0.49
     UP
    0.46
     onları
    0.44
     up
    0.43
     kaž
    0.43
     nghệ
    0.43
     they
    0.43
     chevalier
    0.40
    mila
    0.40
    Activations Density 1.080%

    No Known Activations