© 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. 12772
    Prev
    Next
    INDEX
    Explanations

    references to organized groups and clubs

    oai_token-act-pair · gemini-2.0-flash

    groups

    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
    rungsseite
    -0.79
     يتيمه
    -0.66
     combineReducers
    -0.62
     DialogInterface
    -0.60
    (/[
    -0.59
    WriteTagHelper
    -0.57
     FetchType
    -0.56
    الحياه
    -0.56
     confounded
    -0.55
    createClass
    -0.55
    POSITIVE LOGITS
     members
    0.55
    <bos>
    0.52
    Members
    0.46
    InsertCommand
    0.43
     lyst
    0.42
     Members
    0.41
     discussion
    0.41
    phrag
    0.41
    ыгана
    0.40
    общение
    0.40
    Activations Density 1.177%

    No Known Activations