© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13930
    Prev
    Next
    INDEX
    Explanations

    the word 'the' or possessive words

    oai_token-act-pair · gemini-2.0-flash

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    XmlAccessorType
    -0.83
    StoryboardSegue
    -0.76
    awtextra
    -0.73
    AnimationsModule
    -0.73
     EconPapers
    -0.72
     CURIAM
    -0.72
    addCriterion
    -0.71
    
    -0.71
    Enllaces
    -0.70
    DeleteBehavior
    -0.69
    POSITIVE LOGITS
     very
    3.58
    Very
    3.08
    very
    3.06
     Very
    2.95
     VERY
    2.42
    VERY
    2.39
     muy
    2.27
     très
    2.23
     sehr
    1.88
     Très
    1.71
    Activations Density 4.258%

    No Known Activations