© 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. 3217
    Prev
    Next
    INDEX
    Explanations

    words that describe a relationship or association between two things.

    oai_token-act-pair · gemini-2.0-flash

    book

    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
     related
    -2.47
     Related
    -2.33
    related
    -2.23
    Related
    -2.16
     RELATED
    -2.06
     associated
    -1.83
    RELATED
    -1.74
    associated
    -1.68
     corresponding
    -1.66
     relate
    -1.62
    POSITIVE LOGITS
    -
    1.02
    afficheront
    0.65
     ?>>
    0.57
    
    0.56
    ̍t
    0.55
    artament
    0.55
    TagMode
    0.55
    Tikang
    0.54
    ®-
    0.54
    AxisAlignment
    0.54
    Activations Density 4.986%

    No Known Activations