© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11709
    Prev
    Next
    INDEX
    Explanations

    the word "profile" alongside words that indicate the profiles are being studied

    oai_token-act-pair · gemini-2.0-flash

    profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    帖最后由
    -1.10
     tartalomajánló
    -0.96
    UnusedPrivate
    -0.93
     Efq
    -0.88
    hatenablog
    -0.86
    تقاوى
    -0.85
    RenderAtEndOf
    -0.82
     Paglinawan
    -0.77
     kasarigan
    -0.77
     AssemblyVersion
    -0.77
    POSITIVE LOGITS
    '
    0.58
    Synonymes
    0.56
    й
    0.54
    ager
    0.50
    ός
    0.49
    लेख
    0.48
    треб
    0.48
    bip
    0.47
     zapo
    0.47
    more
    0.47
    Activations Density 1.288%

    No Known Activations