© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4434
    Prev
    Next
    INDEX
    Explanations

    sentences about doing further research or investigation into a topic

    oai_token-act-pair · gemini-2.0-flash

    further

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    UnusedPrivate
    -0.70
    WithIOException
    -0.69
    Portail
    -0.68
    CloseOperation
    -0.68
     otomatig
    -0.67
    原始内容存档于
    -0.66
    存于互联网档案馆
    -0.61
    AndEndTag
    -0.60
     Normdatei
    -0.57
    InjectAttribute
    -0.56
    POSITIVE LOGITS
     further
    2.11
    further
    1.85
     Further
    1.75
    Further
    1.72
     FURTHER
    1.65
     closer
    1.55
     deeper
    1.55
     farther
    1.48
    FURTHER
    1.40
    urther
    1.26
    Activations Density 2.257%

    No Known Activations