© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10095
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive words in the context of art or nature

    oai_token-act-pair · gemini-2.0-flash

    Art and image descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    featureID
    -0.93
     propOrder
    -0.83
     '\\;'
    -0.81
    цездатний
    -0.80
     BoxFit
    -0.71
    OGND
    -0.70
     AssemblyCulture
    -0.69
    ]")]
    -0.67
     protoimpl
    -0.66
    TintMode
    -0.64
    POSITIVE LOGITS
     sw
    0.46
     tỏ
    0.44
    Form
    0.43
     suger
    0.43
    ied
    0.43
    Referències
    0.43
     Form
    0.42
     sugg
    0.41
     Forms
    0.41
     slashed
    0.40
    Activations Density 2.384%

    No Known Activations