© 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. 14641
    Prev
    Next
    INDEX
    Explanations

    the word "general" or the word "when" but sometimes finds related terms such as "states" or "truth"

    oai_token-act-pair · gemini-2.0-flash

    general, when

    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
     purpoſe
    -0.81
    MENAFN
    -0.78
     neceff
    -0.74
     cherchés
    -0.74
     défaite
    -0.73
     متعلقه
    -0.73
     hâte
    -0.72
     pleaſure
    -0.71
     uſe
    -0.71
     ujednoznacz
    -0.70
    POSITIVE LOGITS
    )];
    0.61
     Gosling
    0.58
    epik
    0.57
    ↵↵
    0.56
     initial
    0.55
    hawar
    0.54
     [];
    0.54
    '));
    0.53
    ']>
    0.52
     lenker
    0.52
    Activations Density 0.361%

    No Known Activations