© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1891
    Prev
    Next
    INDEX
    Explanations

    hyphenated words, especially when they start with "pre" or "re"

    oai_token-act-pair · gemini-2.0-flash

    pre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     graded
    -0.61
     consort
    -0.59
    nants
    -0.57
     ministry
    -0.57
     paid
    -0.56
     spin
    -0.56
     pulse
    -0.56
     tested
    -0.56
     lap
    -0.56
     arm
    -0.55
    POSITIVE LOGITS
    rungsseite
    0.73
     avoient
    0.72
     stället
    0.70
     feroit
    0.69
     varandra
    0.69
     étoient
    0.68
     auroit
    0.67
     étoit
    0.66
     precisione
    0.64
     rempliss
    0.61
    Activations Density 8.315%

    No Known Activations