© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6601
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dozen", as well as the word hundreds and the season "fall"

    oai_token-act-pair · gemini-2.0-flash

    dozen

    np_max-act · gemini-2.0-flash

    dozen

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     enfans
    -1.42
     normaux
    -1.32
     ordinaires
    -1.09
     dieux
    -1.07
     chré
    -1.05
     plufieurs
    -1.05
     étoient
    -1.05
     vectorielles
    -1.04
     avoient
    -1.02
     zijne
    -1.01
    POSITIVE LOGITS
     licences
    0.68
    estacks
    0.68
    Brainz
    0.68
    PMailer
    0.66
    ropshire
    0.65
    "}")
    0.63
     licence
    0.62
    stination
    0.62
    pairment
    0.60
    monger
    0.60
    Activations Density 3.022%

    No Known Activations