© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10157
    Prev
    Next
    INDEX
    Explanations

    the letter 'B' at the beginning of a word, often followed by a period or other punctuation

    oai_token-act-pair · gemini-2.0-flash

    B

    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
    parsedMessage
    -0.69
    DeleteBehavior
    -0.67
    setScene
    -0.62
    Espèce
    -0.58
     oprot
    -0.57
    ezers
    -0.54
    getOut
    -0.54
     "..\..\
    -0.53
    RenderAtEndOf
    -0.52
     оригіналу
    -0.51
    POSITIVE LOGITS
    djangoproject
    0.56
     للمعارف
    0.52
    بوابة
    0.50
     Normdatei
    0.46
     الحره
    0.45
    jande
    0.45
     combien
    0.44
    enez
    0.43
    dalen
    0.42
    ighorn
    0.42
    Activations Density 0.543%

    No Known Activations