© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11301
    Prev
    Next
    INDEX
    Explanations

    things that are considered superior

    oai_token-act-pair · gemini-2.0-flash

    superior

    np_max-act · gemini-2.0-flash

    ▁superior

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    endphp
    -0.79
     Pythagoras
    -0.78
     morire
    -0.76
     énergé
    -0.73
     scalars
    -0.72
     colorés
    -0.72
     Aphrodite
    -0.70
     Euripides
    -0.69
     Athenian
    -0.69
     Hellen
    -0.69
    POSITIVE LOGITS
     the
    0.95
     a
    0.71
     an
    0.67
     in
    0.65
     familiar
    0.63
     fact
    0.61
     дописавши
    0.60
    ]));
    0.60
     need
    0.59
     some
    0.59
    Activations Density 2.620%

    No Known Activations