© 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. 10884
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss insignificant items

    oai_token-act-pair · gemini-2.0-flash

    very

    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
    ftagPool
    -0.78
    Short
    -0.74
     Short
    -0.72
     kaarangay
    -0.72
    yntaxException
    -0.71
     Shorter
    -0.69
    webElementXpaths
    -0.66
    Large
    -0.66
    Low
    -0.65
    Thick
    -0.65
    POSITIVE LOGITS
     very
    1.09
     extremely
    0.89
     VERY
    0.79
    very
    0.78
     très
    0.77
     muy
    0.77
    Very
    0.75
    extremely
    0.73
     Very
    0.73
     incredibly
    0.69
    Activations Density 3.749%

    No Known Activations