© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3065
    Prev
    Next
    INDEX
    Explanations

    `Lerp` and `lerp` function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    byshev
    1.71
    ্ম্ম
    1.66
    𝙞
    1.65
    яви
    1.63
    การณ์
    1.61
    পুণ
    1.60
     Qxe
    1.58
    IZATION
    1.58
     явля
    1.56
     आकृति
    1.56
    POSITIVE LOGITS
    clearInterval
    2.01
    कि
    1.90
    ৬
    1.84
    ed
    1.83
    challenged
    1.80
     echip
    1.78
    nearest
    1.77
     Именно
    1.75
     ATTOR
    1.75
    logits
    1.73
    Activations Density 0.000%

    No Known Activations