© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10629
    Prev
    Next
    INDEX
    Explanations

    the word "time"

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ówczas
    -0.65
     totalling
    -0.65
     totalled
    -0.64
     فريبيس
    -0.59
     rê
    -0.56
    RenderAtEndOf
    -0.52
    DebuggerNonUser
    -0.52
     schweren
    -0.51
     wherefore
    -0.51
     **/
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.77
    homonymie
    0.72
    Personendaten
    0.68
    Portály
    0.67
    AutoScaleMode
    0.65
    Portail
    0.65
    pidou
    0.65
    Ἁ
    0.63
    fastjson
    0.61
     frac
    0.61
    Activations Density 0.165%

    No Known Activations