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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5963
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed" or "n" and some random others

    oai_token-act-pair · gemini-2.0-flash

    say "ed"

    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
    ED
    -0.72
    NameInMap
    -0.62
     BoxDecoration
    -0.62
     eneste
    -0.60
    ed
    -0.57
    erecht
    -0.57
     ED
    -0.54
     frågan
    -0.54
    ConstraintMaker
    -0.53
     sièges
    -0.53
    POSITIVE LOGITS
    astéroïdes
    0.57
    '
    0.54
    ’
    0.52
    $'
    0.52
     سكانية
    0.50
     grounded
    0.48
    Diwedd
    0.48
    Билгалдахарш
    0.46
     funded
    0.44
    $​
    0.43
    Activations Density 6.591%

    No Known Activations