© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10816
    Prev
    Next
    INDEX
    Explanations

    lines of code that begin with "@"

    oai_token-act-pair · gemini-2.0-flash

    @

    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
     Efq
    -0.88
     whoſe
    -0.84
     Jefus
    -0.83
     Theſe
    -0.82
     myſelf
    -0.81
     becauſe
    -0.79
    ^(@)
    -0.75
     Chriſt
    -0.75
     himſelf
    -0.75
     themſelves
    -0.73
    POSITIVE LOGITS
    LookAnd
    0.56
    CloseOperation
    0.54
    IUrlHelper
    0.53
    Fns
    0.52
    nocache
    0.51
     MenuView
    0.51
     مشين
    0.51
    SourceChecksum
    0.50
    ynb
    0.49
     protoimpl
    0.49
    Activations Density 0.627%

    No Known Activations