© 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. 7126
    Prev
    Next
    INDEX
    Explanations

    all-uppercase words or acronyms

    oai_token-act-pair · gemini-2.0-flash

    say "AD" 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
    InjectAttribute
    -0.62
     '\\;'
    -0.60
     الرياضيه
    -0.53
     חיצוניים
    -0.53
    "><?=
    -0.53
     "];
    -0.51
    bootstrapcdn
    -0.51
    ConstraintMaker
    -0.50
    adaptiveStyles
    -0.50
    VIAF
    -0.50
    POSITIVE LOGITS
     AD
    0.92
    AD
    0.86
    ad
    0.83
    Ad
    0.79
     ad
    0.78
     Ad
    0.74
    ADH
    0.71
    ADR
    0.71
    ADS
    0.70
    ADU
    0.68
    Activations Density 1.732%

    No Known Activations