© 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. 3985
    Prev
    Next
    INDEX
    Explanations

    words relating to time, especially days or seasons, in a story or article

    oai_token-act-pair · gemini-2.0-flash

    the concept of "each."

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

    each

    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
    Hentet
    -0.66
    ]")]
    -0.64
     geldig
    -0.62
     للمعارف
    -0.59
     otomatig
    -0.58
    ThemeOverlay
    -0.58
     ddelweddau
    -0.57
    AGB
    -0.57
    JNIEnv
    -0.56
    tegen
    -0.56
    POSITIVE LOGITS
     each
    2.88
    Each
    2.31
    each
    2.31
     Each
    2.28
     EACH
    1.84
    EACH
    1.73
     ciascuno
    1.58
     ciasc
    1.56
     chacun
    1.52
     fiecare
    1.45
    Activations Density 4.940%

    No Known Activations