© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7477
    Prev
    Next
    INDEX
    Explanations

    the word "features" and other words related to capabilities or functionalities

    oai_token-act-pair · gemini-2.0-flash

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     feature
    -2.73
     features
    -2.73
     Features
    -2.66
     Feature
    -2.52
    Features
    -2.52
    Feature
    -2.52
    features
    -2.48
    feature
    -2.47
     FEATURES
    -2.19
     FEATURE
    -2.11
    POSITIVE LOGITS
     Prit
    0.52
    MIDDLEWARE
    0.47
    RectangleBorder
    0.46
    AsyncResult
    0.46
     cref
    0.46
    RouterModule
    0.45
     ashes
    0.45
    DataMember
    0.45
     Gant
    0.45
    DOCTYPE
    0.44
    Activations Density 0.419%

    No Known Activations