© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12042
    Prev
    Next
    INDEX
    Explanations

    the word "lot" or phrases containing the word "bit."

    oai_token-act-pair · gemini-2.0-flash

    lot/bit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     whoſe
    -0.56
     Perſ
    -0.53
     Diſ
    -0.52
    }{*}{
    -0.52
    tivism
    -0.51
     Eſ
    -0.51
     itſelf
    -0.50
     Teg
    -0.49
     outer
    -0.48
     Efq
    -0.48
    POSITIVE LOGITS
    VersionUID
    0.78
    ngrx
    0.71
    SerializedSize
    0.70
     snippetHide
    0.69
    DeleteBehavior
    0.69
    sizeCache
    0.69
     defaultstate
    0.68
     estimés
    0.68
    CreateModel
    0.66
    ELINES
    0.65
    Activations Density 0.193%

    No Known Activations