© 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. 12929
    Prev
    Next
    INDEX
    Explanations

    words that relate to dating, family and friends

    oai_token-act-pair · gemini-2.0-flash

    Special gatherings/events

    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
    Биография
    -0.54
     يتيمه
    -0.52
    ніципалі
    -0.52
     em
    -0.50
    tvguidetime
    -0.49
    pecting
    -0.45
    erialized
    -0.44
     LUMP
    -0.43
     EconPapers
    -0.43
     defaultstate
    -0.43
    POSITIVE LOGITS
     aikaa
    0.73
     auffi
    0.72
    Билгалдахарш
    0.67
     Huguen
    0.65
    guenos
    0.60
     zitate
    0.60
     lisesi
    0.60
     ſmall
    0.60
     löytyy
    0.59
     mikina
    0.59
    Activations Density 0.757%

    No Known Activations