© 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. 6774
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to laws, government, and legal processes

    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
     executive
    -1.61
     Chief
    -1.52
    Chief
    -1.48
     Executive
    -1.47
     chief
    -1.45
    Executive
    -1.45
     CEO
    -1.40
    executive
    -1.40
     manager
    -1.32
     Director
    -1.31
    POSITIVE LOGITS
     通販
    0.67
    rungsseite
    0.55
    Autoritní
    0.51
    اریخ
    0.51
    apollo
    0.49
    Identyfik
    0.49
    ]")]
    0.47
    ьаж
    0.47
    migiano
    0.47
    :+:
    0.46
    Activations Density 1.460%

    No Known Activations