© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14818
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'to' preceded or followed by certain words (might, ability, various verbs).

    oai_token-act-pair · gemini-2.0-flash

    technical research contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     sympathi
    -1.23
     stabili
    -1.15
     mobili
    -1.11
     colors
    -1.09
     neighbors
    -1.05
     Еще
    -1.04
     color
    -1.04
     colorful
    -1.03
     honors
    -1.03
     flavors
    -1.00
    POSITIVE LOGITS
     fertili
    0.70
     oxid
    0.57
     AspNetCore
    0.54
     useContext
    0.54
     Савезне
    0.54
    prnewswire
    0.54
    Hentet
    0.52
    CardHeader
    0.49
     EdgeInsets
    0.48
    jfree
    0.47
    Activations Density 4.918%

    No Known Activations