© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12967
    Prev
    Next
    INDEX
    Explanations

    technical information about car engines and transmissions

    oai_token-act-pair · gemini-2.0-flash

    machinery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     &___
    -0.57
    SerializedName
    -0.53
    ModelSerializer
    -0.52
     الحره
    -0.50
    getChild
    -0.49
     uovo
    -0.49
    AddTagHelper
    -0.48
    Slf
    -0.48
     împreună
    -0.47
     dök
    -0.46
    POSITIVE LOGITS
    OPSIS
    0.57
    housie
    0.53
     ComVisible
    0.48
    HtmlAttribute
    0.47
     zet
    0.46
    мум
    0.46
     שוליים
    0.46
    риях
    0.46
     Evaluating
    0.46
    iprot
    0.46
    Activations Density 8.612%

    No Known Activations