© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6328
    Prev
    Next
    INDEX
    Explanations

    phrases of gratitude and references to activities

    oai_token-act-pair · gemini-2.0-flash

    Thanking or sharing

    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
    elemField
    -0.65
    "],
    -0.64
    kloped
    -0.62
    ]),
    -0.61
     مواليد
    -0.61
    ↩
    -0.60
    TintMode
    -0.60
     kasarigan
    -0.58
    "]);
    -0.58
    "},
    -0.58
    POSITIVE LOGITS
     thinking
    0.56
     kind
    0.52
    findpost
    0.52
     fla
    0.50
    toPromise
    0.49
     Humberto
    0.45
     talking
    0.44
     Thought
    0.44
     exporting
    0.43
     think
    0.43
    Activations Density 7.712%

    No Known Activations