© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15279
    Prev
    Next
    INDEX
    Explanations

    descriptions of conflict, betrayal, and fighting against evil

    oai_token-act-pair · gemini-2.0-flash

    unconventional or uncommon terms

    np_token-act-pair-logits · gpt-4o-mini

    Sci-fi/Fantasy action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    》（
    -0.44
    Cie
    -0.40
     ici
    -0.40
    -0.39
    ^
    -0.38
    antd
    -0.38
    onel
    -0.38
    inten
    -0.37
    is
    -0.37
     wat
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.95
     незавершена
    0.80
    ContentAlignment
    0.79
    Datuak
    0.79
    Personendaten
    0.78
    StructEnd
    0.78
    хьтан
    0.76
    archiviato
    0.75
     Diſ
    0.75
     Roskov
    0.74
    Activations Density 5.681%
    No Known Activations