© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    the word "Alle" in HTML code, as well as the words "offering" and "three", and numerals

    oai_token-act-pair · gemini-2.0-flash

    Technical or foreign text

    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
     }</
    -0.60
    )}</
    -0.54
    HomeAsUpEnabled
    -0.50
    }</
    -0.48
     Condol
    -0.47
    клопе
    -0.47
    rieve
    -0.47
    Condolences
    -0.46
    identiality
    -0.45
    Bout
    -0.45
    POSITIVE LOGITS
    featureID
    0.77
    Filmographie
    0.64
    verifyException
    0.61
     ThemeData
    0.61
     Приступљено
    0.59
     joaat
    0.57
     nonUne
    0.54
     userSchema
    0.54
     समीक्षाएं
    0.53
    raborty
    0.50
    Activations Density 0.299%

    No Known Activations