© 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. 7705
    Prev
    Next
    INDEX
    Explanations

    descriptive words about shoe features and their benefits

    oai_token-act-pair · gemini-2.0-flash

    product descriptions

    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
    endphp
    -0.64
    +#+#
    -0.54
    tahui
    -0.53
     للاسماء
    -0.53
     yyj
    -0.53
    +:+
    -0.52
     estimés
    -0.48
    __':
    -0.46
    __":
    -0.46
    raltar
    -0.45
    POSITIVE LOGITS
     ProtoMessage
    0.63
    AnchorStyles
    0.59
    Portail
    0.58
    CppMethod
    0.57
    expandindo
    0.56
    ArgumentParser
    0.55
     Picchu
    0.55
    Geplaatst
    0.54
    queryInterface
    0.53
     disponibilités
    0.52
    Activations Density 6.063%

    No Known Activations