© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9169
    Prev
    Next
    INDEX
    Explanations

    words that follow articles and prepositions

    oai_token-act-pair · gemini-2.0-flash

    say "sports" Method used: 2 — tokens after often name sports/team concepts; say "sports"

    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_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
    MessageOf
    -0.79
     FetchType
    -0.71
     ActivatedRoute
    -0.65
    ondissement
    -0.65
    seamnă
    -0.64
     LEAGUE
    -0.63
    NHL
    -0.62
    League
    -0.61
    AsUp
    -0.61
     незавершена
    -0.60
    POSITIVE LOGITS
    وبه
    0.48
    ciech
    0.47
    Empereur
    0.43
     Normdatei
    0.42
    Бележки
    0.40
    biscuit
    0.40
    empereur
    0.40
    Einzelnachweise
    0.36
    キック
    0.36
    HasKey
    0.36
    Activations Density 7.294%

    No Known Activations