© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15647
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to personal struggles or adversity

    oai_token-act-pair · gemini-2.0-flash

    motivational advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    !*\
    -0.62
    Datuak
    -0.61
     beira
    -0.60
     manqué
    -0.59
     fapt
    -0.58
     StatefulWidget
    -0.58
    ViewFeatures
    -0.58
     Grounds
    -0.57
     brancas
    -0.57
     sociaux
    -0.56
    POSITIVE LOGITS
    ConstraintMaker
    0.70
    ]--;
    0.51
    ."));
    0.48
    Eksterne
    0.46
     isInitialized
    0.44
    istorante
    0.44
    省市镇
    0.43
     Tira
    0.42
    </caption>
    0.42
    esserts
    0.41
    Activations Density 26.284%

    No Known Activations