© 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. 5244
    Prev
    Next
    INDEX
    Explanations

    the word "minor"

    oai_token-act-pair · gemini-2.0-flash

    minor

    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
    NUMX
    -0.89
    )";
    -0.85
    ]**
    -0.84
    cknowled
    -0.77
    .}(
    -0.76
    nefs
    -0.71
    makeText
    -0.70
    ;';
    -0.70
    etheless
    -0.69
    tonsoft
    -0.69
    POSITIVE LOGITS
     représent
    0.67
     voisins
    0.65
    .
    0.64
     épis
    0.63
     titolata
    0.63
    ModelAdmin
    0.63
    was
    0.62
     désol
    0.62
     compréhen
    0.61
    自
    0.60
    Activations Density 0.825%

    No Known Activations