© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11498
    Prev
    Next
    INDEX
    Explanations

    words which could be considered positive adjectives or adverbs

    oai_token-act-pair · gemini-2.0-flash

    bly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     incredible
    -0.59
     tremendous
    -0.58
     immense
    -0.56
     incredibly
    -0.54
     phenomenal
    -0.52
    incredible
    -0.52
     extremely
    -0.52
     amazing
    -0.51
     unbelievable
    -0.50
     unbelievably
    -0.50
    POSITIVE LOGITS
    SequentialGroup
    0.80
     виправивши
    0.79
     noDo
    0.79
    GOTREF
    0.75
    WireFormatLite
    0.74
     للاسماء
    0.73
     يتيمه
    0.71
    Datuak
    0.71
     nahilalakip
    0.70
    mybatisplus
    0.69
    Activations Density 1.937%

    No Known Activations