© 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. 9660
    Prev
    Next
    INDEX
    Explanations

    the prefix "hyper" and related terms like "evidence"

    oai_token-act-pair · gemini-2.0-flash

    hyper

    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
    r
    -0.69
    ไง
    -0.64
      
    -0.60
     Whilst
    -0.54
     whilst
    -0.54
    .
    -0.54
     sva
    -0.54
     responsabilidad
    -0.53
    ֵי
    -0.52
    Whilst
    -0.50
    POSITIVE LOGITS
    >`;
    0.91
     ―――――
    0.88
    ]:
    0.87
    .";
    0.86
     ſind
    0.86
     ་་
    0.84
    ".
    0.83
    "):
    0.82
    "){
    0.79
    ])).
    0.79
    Activations Density 0.678%

    No Known Activations