© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14831
    Prev
    Next
    INDEX
    Explanations

    descriptors of artistic qualities, especially of images and music

    oai_token-act-pair · gemini-2.0-flash

    artistic creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     FetchType
    -0.69
    +#+
    -0.69
    цездатний
    -0.65
    GeoNames
    -0.64
     "..\..\..\
    -0.62
     autorytatywna
    -0.60
    ilant
    -0.58
     zpě
    -0.57
    modb
    -0.57
    ("/{
    -0.57
    POSITIVE LOGITS
     pourrais
    0.51
    فحة
    0.51
     jsPsych
    0.48
    espère
    0.47
     WQS
    0.45
    spender
    0.44
     Wiktionnaire
    0.44
    aimerais
    0.43
     faudrait
    0.42
    imoto
    0.41
    Activations Density 0.731%

    No Known Activations