© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12911
    Prev
    Next
    INDEX
    Explanations

    instances of French contractions and abbreviations common to IRC, especially those starting with the letter "c".

    oai_token-act-pair · gemini-2.0-flash

    unique characters or symbols

    np_token-act-pair-logits · gpt-4o-mini

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     EconPapers
    -0.65
    VersionUID
    -0.59
    ⓘ
    -0.56
    CppMethod
    -0.52
     resourceCulture
    -0.47
    irte
    -0.47
     виправивши
    -0.47
    [:]
    -0.47
    ']))
    -0.47
    onSubmit
    -0.47
    POSITIVE LOGITS
    Pregunta
    0.50
    ńcz
    0.48
     Joi
    0.48
    Portale
    0.48
    binant
    0.47
     GlobalKey
    0.47
     Volkes
    0.47
    FailureListener
    0.45
     betweenstory
    0.45
    DURATION
    0.45
    Activations Density 0.198%

    No Known Activations