© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3060
    Prev
    Next
    INDEX
    Explanations

    words that are often used in scientific or academic documents

    oai_token-act-pair · gemini-2.0-flash

    agent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ë
    -0.41
    vum
    -0.40
    ese
    -0.39
    -
    -0.36
    uc
    -0.35
     Enlarge
    -0.35
     ');
    -0.35
     Volatile
    -0.34
    las
    -0.34
    dah
    -0.34
    POSITIVE LOGITS
     myſelf
    1.21
     Efq
    1.16
     themſelves
    1.10
     purpoſe
    1.09
     itſelf
    1.05
     Monfieur
    1.05
     Jefus
    1.05
    ſelf
    1.04
     pleaſure
    1.03
     himſelf
    1.00
    Activations Density 2.837%

    No Known Activations