© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14251
    Prev
    Next
    INDEX
    Explanations

    historical references to peoples' origins, status, or familial connections

    oai_token-act-pair · gemini-2.0-flash

    were

    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
     is
    -0.83
     kasarigan
    -0.71
     was
    -0.70
     has
    -0.67
    FontOfSize
    -0.65
    +#+#
    -0.58
    was
    -0.58
    has
    -0.52
     hết
    -0.51
    ling
    -0.50
    POSITIVE LOGITS
    abestanden
    0.60
     stars
    0.59
     crocs
    0.57
    niająca
    0.57
     мәкалә
    0.56
     cubes
    0.54
     breeds
    0.52
     ftate
    0.52
     reflectors
    0.52
     arrows
    0.52
    Activations Density 4.926%

    No Known Activations