© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2611
    Prev
    Next
    INDEX
    Explanations

    instances of progress or a state of being

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'process'

    np_token-act-pair-logits · gpt-4o-mini

    process

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    TagMode
    -0.79
     NSCoder
    -0.77
    awtextra
    -0.71
    kuuta
    -0.68
    UnitTesting
    -0.65
     estimés
    -0.62
     ?>>
    -0.61
     ProtoMessage
    -0.61
    Autowired
    -0.59
     ]];
    -0.58
    POSITIVE LOGITS
     process
    1.41
    process
    1.20
     PROCESS
    1.08
     Process
    1.07
    Process
    1.00
     processo
    0.99
     proceso
    0.92
     proses
    0.90
     course
    0.88
    PROCESS
    0.88
    Activations Density 1.594%

    No Known Activations