© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9166
    Prev
    Next
    INDEX
    Explanations

    words related to graphic design and branding

    oai_token-act-pair · gemini-2.0-flash

    Design and visual elements

    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
     Picture
    -0.54
    Graphic
    -0.53
     Graphic
    -0.50
    LikeLike
    -0.49
     Colour
    -0.48
     själ
    -0.48
     herbes
    -0.48
     Schilder
    -0.48
    Välislingid
    -0.48
     Slide
    -0.47
    POSITIVE LOGITS
    ьаж
    0.59
    HomeAsUpEnabled
    0.58
    RegisterType
    0.56
    raszamy
    0.55
    ToAction
    0.55
     block
    0.54
    новниш
    0.54
     type
    0.53
    Personendaten
    0.53
     blocks
    0.51
    Activations Density 5.302%

    No Known Activations