© 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. 6421
    Prev
    Next
    INDEX
    Explanations

    words related to business, management or legal text.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     administ
    -0.72
     ADMINISTRATION
    -0.70
     administration
    -0.67
     admin
    -0.67
     Administ
    -0.67
     Administration
    -0.66
     Admin
    -0.65
     Administrative
    -0.65
     administrative
    -0.65
    Admin
    -0.65
    POSITIVE LOGITS
    دانشنامهٔ
    0.81
    లాలు
    0.66
    StructEnd
    0.66
     Italijanski
    0.64
    principalColumn
    0.62
    Kilder
    0.61
    Comté
    0.60
     dAtA
    0.57
    exitRule
    0.57
     Савез
    0.56
    Activations Density 8.702%

    No Known Activations