© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7671
    Prev
    Next
    INDEX
    Explanations

    snippets of code referring to file handling

    oai_token-act-pair · gemini-2.0-flash

    code and file names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     file
    -1.48
     files
    -1.44
     Files
    -1.18
    file
    -1.18
     File
    -1.13
     FILES
    -1.13
     archivo
    -1.13
     FILE
    -1.12
    files
    -1.09
    ファイル
    -1.09
    POSITIVE LOGITS
    AnimationsModule
    0.63
    NullException
    0.61
     CreateTagHelper
    0.58
    pushFollow
    0.57
    okości
    0.56
    oubliez
    0.55
     فريبيس
    0.54
    forChild
    0.52
    StackNavigator
    0.52
     snippetHide
    0.49
    Activations Density 1.184%

    No Known Activations