© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2756
    Prev
    Next
    INDEX
    Explanations

    several short, common words, particularly next to each other, in the context of a few different topics

    oai_token-act-pair · gemini-2.0-flash

    city centers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     center
    -2.89
     centre
    -2.88
     centers
    -2.70
     centres
    -2.67
    centre
    -2.52
    Center
    -2.50
    center
    -2.45
    Centre
    -2.45
     Center
    -2.44
     Centre
    -2.44
    POSITIVE LOGITS
    Референце
    0.51
    expandindo
    0.50
    minecraftforge
    0.48
     CWE
    0.48
    ConstraintMaker
    0.47
     WQS
    0.45
    ագրություններ
    0.45
    rostis
    0.44
    Démographie
    0.44
     mutagenesis
    0.44
    Activations Density 1.535%

    No Known Activations