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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8242
    Prev
    Next
    INDEX
    Explanations

    words associated with "the same" as well as the word "been" and the word "no" in all different contexts

    oai_token-act-pair · gemini-2.0-flash

    Sameness/resemblance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    };*/
    -0.66
    .")
    -0.63
    "):
    -0.63
     ")
    -0.61
    ()")
    -0.57
     antaranya
    -0.56
    ricians
    -0.52
    "]
    -0.52
     */
    -0.52
    }\]
    -0.50
    POSITIVE LOGITS
    ########.
    1.05
    :✨
    0.96
    PreferredItem
    0.88
    LookAnd
    0.74
     Paglinawan
    0.73
     EconPapers
    0.72
    ContentAsync
    0.71
    ंदीखरीदारी
    0.70
    Vitals
    0.70
    AccessFile
    0.70
    Activations Density 0.634%

    No Known Activations