© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14195
    Prev
    Next
    INDEX
    Explanations

    fragments of code snippets containing keywords such as "here", "the", "put", "in", and "it".

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     avoient
    -0.54
    XMLSchema
    -0.53
     étrangères
    -0.51
     roulant
    -0.48
     citoy
    -0.48
     étrangère
    -0.48
    rxjs
    -0.47
     AssemblyCulture
    -0.46
     scientifiques
    -0.46
     pasaje
    -0.46
    POSITIVE LOGITS
    webElementXpaths
    0.73
    Diweddarwch
    0.68
     للاسماء
    0.66
    ConstraintMaker
    0.63
     CURIAM
    0.61
     MainAxisSize
    0.60
    хьтан
    0.58
     pull
    0.57
    extAlignment
    0.57
     pulled
    0.56
    Activations Density 3.632%

    No Known Activations