© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6634
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to detect elements of programming languages (e.g., Objective-C), French articles and prepositions, spatial relations, lawsuit-related words, and general operation-related terms.

    oai_token-act-pair · gemini-2.0-flash

    code, technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    +:+
    -0.61
     Walkover
    -0.60
    Personendaten
    -0.57
    sizeCache
    -0.57
     pinulongan
    -0.56
     esternos
    -0.54
    νώ
    -0.53
    EndContext
    -0.53
    SOUNDBITE
    -0.51
    Filmografie
    -0.50
    POSITIVE LOGITS
    <bos>
    1.06
    setContentView
    0.54
    )$/,
    0.52
    elung
    0.52
    CGRectMake
    0.50
    خاذ
    0.50
    \{\\
    0.49
    ]='\
    0.49
    '
    0.48
     /\.
    0.48
    Activations Density 1.831%

    No Known Activations