© 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. 10348
    Prev
    Next
    INDEX
    Explanations

    text praising the "ideal" or other superlative qualities of something

    oai_token-act-pair · gemini-2.0-flash

    ideal

    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
     ideal
    -2.34
    Ideal
    -2.14
    ideal
    -2.13
     Ideal
    -2.09
     IDEAL
    -1.70
     ideale
    -1.59
     idéal
    -1.58
    理想
    -1.44
     ideales
    -1.44
     ideally
    -1.40
    POSITIVE LOGITS
    AndEndTag
    0.76
    GEBURTSDATUM
    0.65
    dyž
    0.63
     ویکی‌پدیا
    0.62
    NameInMap
    0.62
    antaranya
    0.59
     AppModule
    0.57
    viewDidLoad
    0.56
     buffet
    0.54
    nodoc
    0.54
    Activations Density 4.335%

    No Known Activations