© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10761
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with creative work and people involved in it

    oai_token-act-pair · gemini-2.0-flash

    creative professions/stories

    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
     sile
    -0.41
     Sosa
    -0.38
     Goff
    -0.37
    Géographie
    -0.36
    ту
    -0.34
    '
    -0.33
    OfYear
    -0.33
     espor
    -0.32
     po
    -0.32
    EXPRESSION
    -0.32
    POSITIVE LOGITS
    исленность
    0.98
     kasarigan
    0.97
    SequentialGroup
    0.92
     Roskov
    0.89
     endwhile
    0.89
     مشين
    0.88
    AddTagHelper
    0.85
    Geplaatst
    0.82
    сылкі
    0.82
     financière
    0.81
    Activations Density 9.141%

    No Known Activations