© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    technical writing related to computer science, medicine, or science in general

    oai_token-act-pair · 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
     houſe
    -0.55
     ſtate
    -0.55
     habet
    -0.55
     purpoſe
    -0.55
     quæ
    -0.54
     reaſon
    -0.53
     cauſe
    -0.53
     eſt
    -0.51
     ſtre
    -0.50
     zijne
    -0.50
    POSITIVE LOGITS
     виправивши
    0.92
     kaarangay
    0.85
    ViewFeatures
    0.81
     дописавши
    0.78
    WriteBarrier
    0.77
     مشين
    0.75
    ########.
    0.72
    "]);
    0.72
    IVEREF
    0.72
     --}}
    0.69
    Activations Density 45.055%

    No Known Activations