© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9875
    Prev
    Next
    INDEX
    Explanations

    a combination of the word "have" and time-related words, and it also identifies subjective opinions

    oai_token-act-pair · gemini-2.0-flash

    the concept of 'time'

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

    time

    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
    Παραπομπές
    -0.66
    AndEndTag
    -0.55
    XmlAccessorType
    -0.53
    קישורים
    -0.51
    зайн
    -0.50
    ագրություններ
    -0.49
    tvguidetime
    -0.47
    انيف
    -0.46
    lrrrr
    -0.45
    twimg
    -0.45
    POSITIVE LOGITS
     time
    3.09
    time
    2.31
     TIME
    2.05
     Time
    2.05
    Time
    2.03
     tijd
    1.86
     tiempo
    1.79
    TIME
    1.76
    时间
    1.71
     времени
    1.66
    Activations Density 2.065%

    No Known Activations