© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11531
    Prev
    Next
    INDEX
    Explanations

    words related to food and restaurants

    oai_token-act-pair · gemini-2.0-flash

    joints

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Бахар
    -0.73
    XmlAccessorType
    -0.72
    quelize
    -0.71
    rrggbb
    -0.69
    webElementGuid
    -0.68
     BoxFit
    -0.67
     HasFactory
    -0.63
    TagMode
    -0.60
    ariConfig
    -0.59
    mongoose
    -0.59
    POSITIVE LOGITS
     joint
    1.23
     joints
    1.13
    joint
    1.02
    Joint
    0.90
     Joints
    0.89
     Joint
    0.89
    joints
    0.88
     JOINT
    0.87
    JOINT
    0.74
     dives
    0.52
    Activations Density 2.792%

    No Known Activations