© 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. 631
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to official procedures and documents, especially those related to address verification

    oai_token-act-pair · gemini-2.0-flash

    variants of "consist"

    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
     included
    -1.04
     Included
    -0.93
    included
    -0.91
     include
    -0.88
    Included
    -0.85
    include
    -0.82
    awtextra
    -0.78
    Including
    -0.76
    Include
    -0.75
     INCLUDED
    -0.75
    POSITIVE LOGITS
     consist
    1.13
     consists
    1.13
     consisting
    1.11
     contains
    0.99
     comprises
    0.94
     contain
    0.93
     embody
    0.91
     consisted
    0.87
     Contain
    0.85
     comprise
    0.85
    Activations Density 2.198%

    No Known Activations