© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12795
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "be," "can," and "have."

    oai_token-act-pair · 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
    новниш
    -0.69
     print
    -0.60
     stuffing
    -0.60
     complete
    -0.58
     alternate
    -0.58
     matching
    -0.58
     ruling
    -0.58
     free
    -0.58
     pitching
    -0.58
     mapping
    -0.57
    POSITIVE LOGITS
    évaluateur
    0.53
    saraba
    0.50
    <bos>
    0.49
     Hoje
    0.47
    isContained
    0.46
     esternos
    0.46
    intios
    0.45
     CreateTagHelper
    0.44
    HasBeenSet
    0.43
    říve
    0.43
    Activations Density 4.522%

    No Known Activations