© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15014
    Prev
    Next
    INDEX
    Explanations

    abbreviations and references to theorems or mathematical proofs

    oai_token-act-pair · gemini-2.0-flash

    Proofs/formal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -1.07
     mergeFrom
    -0.88
     referenties
    -0.80
    Geplaatst
    -0.74
    MessageOf
    -0.73
    følgelig
    -0.72
     noDo
    -0.71
    /*
    -0.69
     unknownFields
    -0.69
    HideFlags
    -0.68
    POSITIVE LOGITS
    CppMethod
    0.53
     fact
    0.48
    stdc
    0.47
     quelque
    0.47
     بش
    0.47
     TextInputType
    0.45
    CEED
    0.45
    ധ
    0.44
     terlebih
    0.43
    ÁND
    0.43
    Activations Density 4.900%

    No Known Activations