© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    Java code related to overriding methods

    oai_token-act-pair · gemini-2.0-flash

    @

    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
    évaluateur
    -0.97
    styleType
    -0.91
    IContainer
    -0.87
    parsedMessage
    -0.87
    IsContent
    -0.87
    #+#
    -0.85
     للمعارف
    -0.83
    :+:
    -0.82
     חיצוניים
    -0.79
     nahilalakip
    -0.79
    POSITIVE LOGITS
    Over
    0.46
     over
    0.44
    over
    0.41
     Over
    0.38
    o
    0.37
    res
    0.35
    Empty
    0.34
     (
    0.33
    ó
    0.32
    SuppressMessage
    0.31
    Activations Density 0.863%

    No Known Activations