© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9964
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns as well as words related to business

    oai_token-act-pair · gemini-2.0-flash

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     We
    -0.74
    We
    -0.66
     kami
    -0.66
     our
    -0.65
     we
    -0.65
     ourselves
    -0.59
     нами
    -0.57
     мы
    -0.55
    我們
    -0.54
     mūsų
    -0.54
    POSITIVE LOGITS
    enumi
    0.79
     שוליים
    0.73
    TemporalType
    0.69
    GOTREF
    0.69
     AttributeSet
    0.68
    verwijspagina
    0.64
    ITUD
    0.63
    AccessFile
    0.60
     Merk
    0.60
    URLException
    0.59
    Activations Density 4.793%

    No Known Activations