© 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. 14863
    Prev
    Next
    INDEX
    Explanations

    the name "Bill"

    oai_token-act-pair · gemini-2.0-flash

    Bill/William

    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
    AccessorTable
    -0.59
     invokingState
    -0.59
    StructEnd
    -0.56
     INTERESAR
    -0.54
    TemporalType
    -0.54
    pushFollow
    -0.53
    addComponent
    -0.53
    LError
    -0.51
    cheria
    -0.51
    prepareStatement
    -0.50
    POSITIVE LOGITS
    MergeFrom
    0.57
    ölkerung
    0.53
     Roskov
    0.51
    setVerticalGroup
    0.50
     sarili
    0.48
     referenties
    0.47
    OpenHelper
    0.47
    ochim
    0.47
    AsUp
    0.46
    RTLD
    0.45
    Activations Density 0.825%

    No Known Activations