© 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. 1355
    Prev
    Next
    INDEX
    Explanations

    personal narratives of past events and arguments.

    oai_token-act-pair · gemini-2.0-flash

    Social problems

    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
     were
    -2.05
    Were
    -1.77
     Were
    -1.77
    were
    -1.72
     WERE
    -1.59
    Was
    -1.52
     Was
    -1.41
     was
    -1.41
    was
    -1.36
     étaient
    -1.34
    POSITIVE LOGITS
    höhung
    0.53
    ————————————
    0.47
     may
    0.46
    ved
    0.46
     can
    0.43
    deur
    0.43
     must
    0.39
    jst
    0.38
     made
    0.38
     valsty
    0.37
    Activations Density 5.587%

    No Known Activations