© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4923
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to requests, offers and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    interested

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    findpost
    -0.80
     estekak
    -0.71
    MENAFN
    -0.63
     تانيه
    -0.60
     }}"></
    -0.59
    kuuta
    -0.59
     cauſe
    -0.58
     caufe
    -0.57
    ⓧ
    -0.57
    Lähteet
    -0.57
    POSITIVE LOGITS
     interested
    1.82
     interest
    1.77
    interested
    1.62
     Interested
    1.60
     Interest
    1.56
     INTEREST
    1.52
    Interest
    1.49
    interest
    1.48
    INTEREST
    1.43
    Interested
    1.42
    Activations Density 0.921%

    No Known Activations