© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4926
    Prev
    Next
    INDEX
    Explanations

    snippets of C and C++ (and possibly other similar) code

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     للمعارف
    -0.84
    complexContent
    -0.71
    ագրություններ
    -0.65
    LookAnd
    -0.65
    ✭✭
    -0.65
     كومونز
    -0.65
    ChildScrollView
    -0.65
     doPost
    -0.62
     TextAppearance
    -0.62
     estekak
    -0.59
    POSITIVE LOGITS
     resistance
    0.57
    Datuak
    0.51
    geführten
    0.47
    isateur
    0.46
    滋
    0.46
     appointed
    0.46
    нительно
    0.45
     carefully
    0.44
    lu
    0.43
     resist
    0.43
    Activations Density 1.839%

    No Known Activations