© 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. 13124
    Prev
    Next
    INDEX
    Explanations

    instances of pronouns followed by auxiliary verbs, conditional conjunctions, and some adverbs.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     DAF
    -0.65
    crollView
    -0.51
     ::=
    -0.50
    qvarna
    -0.50
    idung
    -0.50
    LookAnd
    -0.49
    viewDidLoad
    -0.48
     speed
    -0.48
    hasMoreElements
    -0.47
    [...,
    -0.46
    POSITIVE LOGITS
     pubblicità
    0.65
     razões
    0.63
     betweenstory
    0.63
     Roskov
    0.62
     AspNetCore
    0.59
     récentes
    0.56
     ragioni
    0.56
     समीक्षाएं
    0.56
     actuels
    0.55
     dramatique
    0.54
    Activations Density 6.865%

    No Known Activations