© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    characters and punctuation commonly found in URLs and code

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Gön
    -0.42
    dracht
    -0.40
     soggetto
    -0.39
    frame
    -0.38
     miglior
    -0.38
     prosím
    -0.37
     felhasznál
    -0.37
     sula
    -0.37
     adieu
    -0.36
     keinem
    -0.36
    POSITIVE LOGITS
    Tembelea
    0.86
     חיצוניים
    0.84
    ंदीखरीदारी
    0.81
    CrossRef
    0.75
     nakalista
    0.73
    KommentareTeilen
    0.71
    الإنجليزية
    0.71
    actéristique
    0.69
     Audiodateien
    0.69
    BagConstraints
    0.69
    Activations Density 2.967%

    No Known Activations