© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7373
    Prev
    Next
    INDEX
    Explanations

    a mix of nouns related to gifts and travel and some common verbs around them

    oai_token-act-pair · gemini-2.0-flash

    products and shopping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     للاسماء
    -0.45
    ByExample
    -0.42
    WithMany
    -0.41
    almi
    -0.41
    ima
    -0.41
    клон
    -0.41
    Segoe
    -0.41
    ArgsConstructor
    -0.41
    StreetMap
    -0.40
    ALS
    -0.40
    POSITIVE LOGITS
    ंदीखरीदारी
    0.79
    aarrggbb
    0.73
     surla
    0.72
     дописавши
    0.68
     تانيه
    0.64
    ]--;
    0.63
    +#+#
    0.61
     transfieras
    0.60
    ItemBackground
    0.59
    Portály
    0.58
    Activations Density 2.423%

    No Known Activations