© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3816
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to creatures, leadership or labels

    oai_token-act-pair · gemini-2.0-flash

    creatures, exploration, conquest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    uttavia
    -0.47
     antaranya
    -0.46
     vuitton
    -0.46
     mengal
    -0.44
    //
    -0.44
     Oakes
    -0.43
    Література
    -0.42
    ῖ
    -0.41
    ANSA
    -0.41
    Im
    -0.40
    POSITIVE LOGITS
    +#+#
    0.80
     متعلقه
    0.77
    ReusableCell
    0.75
    setVerticalGroup
    0.74
    AndEndTag
    0.72
     <=",
    0.70
     CreateTagHelper
    0.68
    ViewImports
    0.67
    ViewFeatures
    0.65
     مشين
    0.64
    Activations Density 2.518%

    No Known Activations