© 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. 14219
    Prev
    Next
    INDEX
    Explanations

    the preposition "on" and words that commonly follow it like, time, air, table

    oai_token-act-pair · gemini-2.0-flash

    words related to 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
    CloseOperation
    -1.08
     estekak
    -1.03
    AndEndTag
    -1.02
    ьаж
    -0.89
    RectangleBorder
    -0.84
     <<<<<<<<<<<<<<
    -0.84
    __':
    -0.83
    SourceChecksum
    -0.82
     IBOutlet
    -0.80
    MarshalTo
    -0.79
    POSITIVE LOGITS
     time
    1.59
    time
    1.36
     Time
    1.20
    Time
    1.19
    TIME
    1.11
     TIME
    1.07
    время
    0.93
     timely
    0.91
     시간
    0.90
     tiempo
    0.89
    Activations Density 1.207%

    No Known Activations