© 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. 14850
    Prev
    Next
    INDEX
    Explanations

    code snippets and Google protocol buffer references

    oai_token-act-pair · gemini-2.0-flash

    protobuf

    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
     Helene
    -0.46
     Tango
    -0.44
     tango
    -0.44
     confound
    -0.44
    adze
    -0.43
    {"
    -0.42
    return
    -0.42
    間違い
    -0.42
     unseen
    -0.41
    주의
    -0.40
    POSITIVE LOGITS
    تقاوى
    1.09
    MigrationBuilder
    1.05
     незавершена
    0.96
    tagHelperRunner
    0.85
    :✨
    0.84
    Portale
    0.82
     beginnetje
    0.81
     ComVisible
    0.79
    CloseOperation
    0.78
     kaarangay
    0.77
    Activations Density 2.991%

    No Known Activations