© 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. 5722
    Prev
    Next
    INDEX
    Explanations

    language related to doing good.

    oai_token-act-pair · gemini-2.0-flash

    Seal

    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
     scholarship
    -1.34
     Scholarship
    -1.26
    Scholarship
    -1.19
    scholars
    -1.14
     scholarships
    -1.13
     SCHOLAR
    -1.09
     Scholarships
    -1.08
    Scholars
    -1.04
     Scholar
    -0.88
     Scholars
    -0.79
    POSITIVE LOGITS
    webElementXpaths
    0.59
    RepeatedField
    0.53
     архивлан
    0.52
    Хьажоргаш
    0.52
    flage
    0.52
    raft
    0.51
     deportivos
    0.51
     fédé
    0.50
    Hozzáférés
    0.50
     Dunbar
    0.50
    Activations Density 2.223%

    No Known Activations