© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5293
    Prev
    Next
    INDEX
    Explanations

    the word "a" preceding a noun or adjective with a positive connotation, as well as some proper nouns

    oai_token-act-pair · gemini-2.0-flash

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    COUVER
    -0.60
    ">'.$
    -0.52
    posables
    -0.46
    unków
    -0.46
    uko
    -0.46
     Much
    -0.46
    valg
    -0.45
    ケート
    -0.45
    出版年
    -0.45
    Istorija
    -0.45
    POSITIVE LOGITS
     good
    2.58
    good
    2.31
    Good
    2.14
     Good
    1.97
    GOOD
    1.85
     GOOD
    1.84
     buena
    1.59
     fair
    1.49
     bonne
    1.47
     buenas
    1.44
    Activations Density 2.251%

    No Known Activations